IEEE/CAA JAS第7卷第4期发表了 关于智能控制、稳定性分析、机器人、图像处理、智能车辆、机器学习、多智能体系统等方向论文。欢迎阅览。 01 Qinglai Wei, Hongyang Li and Fei-Yue Wang, Parallel Control for Continuous-Time Linear Systems: A Case Study , IEEE/CAA J. Autom. Sinica , vo l. 7, no. 4, pp. 919-928, July 2020. Highlights: ❖ A new parallel control structure for continuous-time linear systems is proposed. ❖ The parallel controller is proposed based on parallel control theory. ❖ The parallel controller considers both system state and control as input. ❖ The parallel controller can avoid the disadvantages of state feedback control. 02 Pierluigi Di Franco, Giordano Scarciotti and Alessandro Astolfi, Stability of Nonlinear Differential-Algebraic Systems Via Additive Identity, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 929-941, July 2020. Highlights: ❖ Representation of DAE systems as feedback interconnection. ❖ Stability analysis forDAE systems via Lyapunov Method and Small Gain-like arguments. ❖Stability analysis for nonlinear mechanical systems with holonomic constraints. ❖Stability analysis of Lipschitz DAE systems. 03 Jacob H. White and Randal W. Beard, An Iterative Pose Estimation Algorithm Based on Epipolar Geometry With Application to Multi-Target Tracking , IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 942-953, July 2020. Highlights: ❖ This paper introduces a new algorithm for estimating the relative pose of a moving camera. ❖ A novel optimization algorithm solves for the relative pose using the epipolar constraint. ❖ Applications include multi-target tracking, visual odometry, and 3D scene reconstruction. ❖ If IMU information is available, it is used to seed the pose estimation algorithm. ❖ Real-time execution of the algorithm is demonstrated on an embedded flight platform. 04 Haowei Lin, Bo Zhao, Derong Liu and Cesare Alippi, Data-based Fault Tolerant Control for Affine Nonlinear Systems Through Particle Swarm Optimized Neural Networks, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 954-964, July 2020. Highlights: ❖ A data-based fault tolerant control scheme is investigated. ❖ The unknown system dynamics is approximated by PSO-NN identifier. ❖ The HJB equation is solved with a high successful rate by the PSOCNN. ❖ The online fault tolerant control is shown to be optimal. 05 Xiaodong Zhao, Yaran Chen, Jin Guo and Dongbin Zhao, A Spatial-Temporal Attention Model forHuman Trajectory Prediction, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 965-974, July 2020. Highlights: ❖ Study the trajectory prediction jointly with temporal and spatial affinities. ❖ A LSTM model that uses attention mechanism to improve the accuracy of trajectory prediction . ❖ An experimental error analysis using data based on both world plane and image plane. 06 Ali Forootani, Raffaele Iervolino, Massimo Tipaldi and Joshua Neilson, Approximate Dynamic Programming for Stochastic Resource Allocation Problems, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 975-990, July 2020. Highlights: ❖ MDP based resource allocation problem is proposed. ❖ MPC is considered in the framework of the MDP. ❖ Algorithms suitable for computer implementation are proposed. ❖ Compressive sampling is considered for ADP. ❖ Linear architecture is considered for ADP. 07 Liang Yang, Bing Li, Wei Li, Howard Brand, Biao Jiang and Jizhong Xiao, Concrete Defects Inspection and 3D Mapping Using CityFlyer Quadrotor Robot, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 991-1002, July 2020. Highlights: ❖ A high-quality labeled dataset for crack and spalling detection, which is the first publicly available dataset for visual inspection of concrete structures. ❖ A robotic inspection system with visual-inertial fusion to obtain pose estimation using an RGB-D camera and an IMU. ❖ A depth in-painting model that allows depth hole in-painting in an end-to-end approach with real-time performance. ❖ A multi-resolution model that adapts to image resolution changes and allows accurate defect detection in the field. 08 Giancarlo Fortino, Antonio Liotta, Fabrizio Messina, Domenico Rosaci and Giuseppe M. L. Sarnè, Evaluating Group Formation in Virtual Communities, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1003-1015, July 2020. Highlights: ❖ The problem of forming effective groups in virtual communities is addressed. ❖The proposed solution exploits trust information without significant overhead by adopting local reputation instead of global reputation. ❖An index to measure the effectiveness of group formation is introduced, as well as an algorithm to drive group formation as proof of concept. ❖Experimental trials performed on two data sets extracted from social networks have shown that the adoption of the proposed solution offer significant advantages. 09 Chinthaka Premachandra, Dang Ngoc Hoang Thanh, Tomotaka Kimura and Hiroharu Kawanaka, A Study on Hovering Control of Small Aerial Robot by Sensing Existing Floor Features, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1016-1025, July 2020. Highlights: ❖ Hovering control of small aerial robot. ❖Image processing using small-type and low-weight microcontrollers. ❖Specific image feature point detection by weak directional pattern analysis. ❖On-board camera image processing based autonomous flight control of UAV. ❖Simple and low-cost image noise removal process. 10 Mohammadhossein Ghahramani, Yan Qiao, MengChu Zhou, Adrian O’Hagan and James Sweeney, AI-Based Modeling and Data-Driven Evaluation for Smart Manufacturing Processes, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1026-1037, July 2020. Highlights: ❖ To address this concern, a dynamic feature selection model based on an integrated algorithm including a meta-heuristic method (GA) and an artificial neural network is proposed. ❖The implemented algorithm considers two major conflicting objectives: minimizing the number of features and maximizing the classification performance. ❖The proposed AI-based multi-objective feature selection method together with an efficient classification algorithm can enables decision makers to scrutinize manufacturing processes. 11 Yaojie Zhang, Bing Xu and Tiejun Zhao, Convolutional Multi-Head Self-Attention on Memory for Aspect Sentiment Classification, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1038-1044, July 2020. Highlights: ❖ Using convolution and self-attention to capture semantic information of n-gram and sequence itself. ❖The aspect-sequence modeling ability and network parallelism of memory network are preserved. ❖Can complete ACSA and ATSA tasks and win in baseline. 12 Chaoyue Zu, Chao Yang, Jian Wang, Wenbin Gao, Dongpu Cao and Fei-Yue Wang, Simulation and Field Testing of Multiple Vehicles Collision Avoidance Algorithms, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1045-1063, July 2020. Highlights: ❖ A distributed real-time MVCA algorithm is proposed by extending the reciprocal n-body collision avoidance method and enables the intelligent vehicles to choose their destinations and control inputs independently. ❖The effects of latency and packet loss on MVCA are also statistically investigated through theoretically formulating broadcasting process based on one-dimensional Markov chain and the results uncover that the tolerant delay should not exceed the half of deciding cycle of trajectory planning, and shortening the sending interval could alleviate the negative effects caused by the packet loss to an extent. ❖The MVCA was tested by a real intelligent vehicle, the information on obstacles and the latitude and longitude of the vehicle were input into the algorithm, 13 Kritika Bansal and Pankaj Mukhija, Aperiodic Sampled-Data Control of Distributed Networked Control Systems Under Stochastic Cyber-Attacks, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1064-1073, July 2020. Highlights: ❖ A hybrid aperiodic sampled-data mechanism for distributed networked control systems under stochastic deception attacks is introduced to alleviate the problem of computational load, energy consumption and communication load. ❖A more general attack scenario on distributed networked control systems is considered whereby stochastic deception attacks of different intensity on different subsystems may occur. ❖The implementation of self-triggering strategy alone for distributed networked control systems under attack is also presented. ❖The analysis of the proposed strategy for an isolated system is presented as a special case. Also, minimum inter-event time is obtained for an isolated system under deception attack. 14 Chao Han and Yuzhen Shen, Three-Dimensional Scene Encryption Algorithm Based on Phase Iteration Algorithm of the Angular-Spectral Domain, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1074-1080, July 2020. Highlights: ❖ An accurate angular spectrum diffraction is used to reduce the loss of information transmission. ❖The combination of the angular spectrum diffraction and the three - phase iterative algorithm improves the security of the encrypted information. ❖The algorithm proposed can achieve the encryption and decryption of 3D scenes and increase the capacity of the encrypted information. 15 Xiaoyuan Wang, Chenxi Jin, Xiaotao Min, Dongsheng Yu and Herbert Ho Ching Iu, An Exponential Chaotic Oscillator Design and Its Dynamic Analysis, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1081-1086, July 2020. Highlights: ❖ Exponential nonlinear term This exponentially nonlinear term may make the new chaotic system have better performance. And the effectiveness of this exponential chaotic system has been proved by various theoretical analyses. ❖NIST test The exponential chaotic system passed all fifteen tests, but the Lü system passed only fourteen of them. Also the exponential chaotic system has 9 tests with P-values greater than the Lü system in all 15 tests. ❖Circuit This paper has designed a circuit corresponding to the exponential chaotic system. And the simulation results of Multisim are consistent with the theoretical analysis. 16 Mohammad Javad Morshed, A Nonlinear Coordinated Approach to Enhance the Transient Stability of Wind Energy-Based Power Systems, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1087-1097, July 2020. Highlights: ❖ Introduce a new nonlinear coordination method based on MIMO zero dynamics approach. ❖Coordinate controllers of DFIG and synchronous generators (SGs) in multi-machine power systems. ❖Propose a coordinated framework for large scale power systems with n-DFIG and m-SG. ❖Enhance transient and voltage stability of inter-connected power systems. ❖The proposed approach is implemented to the IEEE 39-bus power systems. 17 Chao Deng, Weinan Gao and Weiwei Che, Distributed Adaptive Fault-Tolerant Output Regulation of Heterogeneous Multi-Agent Systems With Coupling Uncertainties and Actuator Faults, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1098-1106, July 2020. Highlights: ❖ A novel distributed adaptive fault-tolerant control method is proposed to solve the fault-tolerant output regulation problem for heterogeneous MASs with matched system uncertainties and mismatched coupling uncertainties among subsystems. ❖Different from the existing distributed fault-tolerant control result, a more general directed network topology is considered in this paper. ❖ A novel sufficient condition with cyclic-small-gain condition is proposed by using the linear matrix inequality technique. 18 Jing Huang, Yimin Chen, Xiaoyan Peng, Lin Hu and Dongpu Cao, Study on the Driving Style Adaptive Vehicle Longitudinal Control Strategy, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1107-1115, July 2020. Highlights: ❖ A driver-adaptive fusion control strategy of Adaptive Cruise Control and Collision Avoidance was proposed. ❖Different styles of divers’ driving behavioural data were collected via driving simulator experiments, corresponding driving behaviour characteristics were extracted and used in the driver-adaptive control. ❖Real-time recognition of driving style was achieved based on fuzzy reasoning rule. ❖The effect of the fusion control strategy was validated by virtual experiments. 19 Qi Wu, Li Yu, Yao-Wei Wang and Wen-An Zhang, LESO-based Position Synchronization Control for Networked Multi-Axis Servo Systems With Time-Varying Delay, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1116-1123, July 2020. Highlights: ❖ It is demonstrated that the proposed approach can deal with the effects of system uncertainty, external disturbance, and short time-varying for the NMASS. ❖It is rigorously proved that the closed-loop control system under the proposed controller is bounded-input-bounded-output (BIBO) stable. ❖It is verified that the proposed method has better tracking and synchronization performance than the improve PID-based method by testing on a four-axis NMASS experimental platform. ❖The bandwidth-parameterization tuning method is applied in both controller design and observer design, so that the number of parameters that need to be adjusted is greatly reduced. 20 Longwei Fang, Zuowei Wang, Zhiqiang Chen, Fengzeng Jian, Shuo Li and Huiguang He, 3D Shape Reconstruction of Lumbar Vertebra From Two X-ray Images and a CT Model, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1124-1133, July 2020. Highlights: ❖ This paper introduces a novel method that use prior model and two x-ray images to reconstruct 3D vertebra. ❖We use the CT data of a vertebra specimen to provide both the shape mesh and the intensity model, and only one prior model used in our method. ❖We combine the elastic-mesh-based and statistical-intensity-model-based methods, which can provide efficient and robust 3D vertebra reconstruction. 21 Jiahai Wang, Yuyan Sun, Zizhen Zhang and Shangce Gao, Solving Multitrip Pickup and Delivery Problem With Time Windows and Manpower Planning Using Multiobjective Algorithms, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1134-1153, July 2020. Highlights: ❖ A multiobjective pickup and delivery problem with time windows and manpower planning is introduced. ❖A multiobjective iterated local search algorithm with adaptive neighborhood is proposed. ❖The nature of objective functions and the properties of the problem are analyzed. ❖The benefits of multiobjective optimization are discussed. 22 Jin Xu, Wei Wu, Keyou Wang and Guojie Li, C-Vine Pair Copula Based Wind Power Correlation Modelling in Probabilistic Small Signal Stability Analysis, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1154-1160, July 2020. Highlights: ❖ In this paper, the C-vine pair copula theory is introduced to describe the complicated dependence of multidimensional wind power injection, and samples obeying this dependence structure are generated. ❖The probabilistic stability of power system integrated with six wind farms is investigated by performing the Monte Carlo simulations under different correlation models and different operating conditions scenarios. ❖In the case study of a modified New England test system, the simplified pair copula construction (sPCC) with C-vine structure proves to have a better reflection of the actual dependence than the linear correlation coefficient (LCC) model and multivariate normal copula model. 23 Shengwen Xiang, Hongqi Fan and Qiang Fu, Distribution of Miss Distance for Pursuit-Evasion Problem, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1161-1168, July 2020. Highlights: ❖ An analytic method for solving the distribution of miss distance is proposed by integrating the error model of zero-effort miss distance. ❖Four different types of Bang-Bang disturbances are considered specifically. ❖Results provide a powerful tool for the design, analysis and performance evaluation of pursuit-evasion problems. 24 Teng Liu, Hong Wang, Bin Tian, Yunfeng Ai and Long Chen, Parallel Distance: A New Paradigm of Measurement for Parallel Driving, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1169-1178, July 2020. Highlights: ❖ Parallel driving 3.0 system as potential autonomous driving system is essentially discussed. ❖Parallel distance framework is presented to measure real and artificial world. ❖Techniques related to multiple distance calculation are quantified and compared. ❖Practical applications of parallel distance framework is introduced and outlined. 25 Lan Jiang, Hongyun Huang and Zuohua Ding, Path Planning for Intelligent Robots Based on Deep Q-learning With Experience Replay and Heuristic Knowledge, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1179-1189, July 2020. Highlights: ❖ Fast convergence and Better strategy ❖Deep Q-learning ❖Experience replay ❖Heuristic knowledge 26 Luping Wang and Hui Wei, Avoiding Non-Manhattan Obstacles Based on Projection of Spatial Corners in Indoor Environment, IEEE/CAA J. Autom. Sinica , vol. 7, no. 4, pp. 1190-1200, July 2020. Highlights: ❖ A method is presented to avoid non-Manhattan obstacles in an indoor environment from a monocular camera. ❖The method can cope with the non-Manhattan obstacle without prior training, making it practical and efficient for a navigating robot. ❖The approach is robust against changes in illumination and color in 3D scenes, without the knowledge of camera’s intrinsic parameters, nor of the relation between the camera and world.
Jounal of Cotton Research Cotton High Speed Phenotyping Thematic Series Call For Paper Coordinator: Professor Eric F. Hequet, Texas Tech University, USA; Dr. Glen Ritchie, Texas Tech University, USA High speed phenotyping is critical to improve cotton research and production. It can be applied to large scale commercial fields, research fields, breeding lines, and even at the individual plant level. The main goals are to improve yield, fiber quality, stress and disease resistance, etc. Recently, advances in high speed phenotyping in cotton have been achieved. The Journal of Cotton Research is hosting a thematic series on this topic. The research community is encouraged to share original findings, methodology, results, databases, and/or software and opinions. Scopes that may be covered in the submissions may include, but are not limited to the following: 1. Platform design: air-based and/or land-based; 2. Data capture and processing: sensors (RGB, IR, multispectral, sonic, etc.), integration of multiple sensors, information processing technologies; 3. Data analysis and Metadata: analysis of very large data sets, validation with ground truth, practical application examples (breeding programs, site specific irrigation scheduling, etc.). Submission Deadline: April 30, 2019 期刊简介、APC及稿酬等
图像处理与计算机视觉:基础,经典以及最近发展(1 )序 1. 为什么要写这篇文章 从2002年到现在,接触图像快十年了。虽然没有做出什么很出色的工作,不过在这个领域摸爬滚打了十年之后,发现自己对图像处理和计算机视觉的感情越来越深厚。下班之后看看相关的书籍和文献是一件很惬意的事情。平常的一大业余爱好就是收集一些相关的文章,尤其是经典的文章,到现在我的电脑里面已经有了几十G的文章。写这个文档的想法源于我前一段时间整理文献时的一个突发奇想,既然有这个多文献,何不整理出其中的经典,共享给大家呢。于是当时即兴写了一个《图像处理与计算机视觉中的经典论文》。现在来看,那个文档写得及其拙劣,所共享的论文也非常之有限。就算如此,还是得到了一些网友的夸奖,心里感激不尽。因此,一直想下定决心把这个文章给完善,力求做到尽量全面。 本文是对现有的图像处理和计算机视觉的经典书籍(后面会有推荐)的一个补充。一般的图像处理书籍都是介绍性的介绍某个方法,在每个领域内都会引用几十上百篇参考文献。有时候想深入研究这个领域的时候却发现文献太多,不知如何选择。但实际上在每个领域都有那么三五篇抑或更多是非读不可的经典文献。这些文献除了提出了很经典的算法,同时他们的Introduction和Related work也是对所在的领域很好的总结。读通了这几篇文献也就等于深入了解了这个领域,比单纯的看书收获要多很多。写本文的目的就是想把自己所了解到的各个领域的经典文章整理出来,不用迷失在文献的汪洋大海里。 2. 图像处理和计算机视觉的分类 按照当前流行的分类方法,可以分为以下三部分: 图像处理: 对输入的图像做某种变换,输出仍然是图像,基本不涉及或者很少涉及图像内容的分析。比较典型的有图像变换,图像增强,图像去噪,图像压缩,图像恢复,二值图像处理等等。基于阈值的图像分割也属于图像处理的范畴。一般处理的是单幅图像。 图像分析: 对图像的内容进行分析,提取有意义的特征,以便于后续的处理。处理的仍然是单幅图像。 计算机视觉: 对图像分析得到的特征进行分析,提取场景的语义表示,让计算机具有人眼和人脑的能力。这时处理的是多幅图像或者序列图像,当然也包括部分单幅图像。 关于图像处理,图像分析和计算机视觉的划分并没有一个很统一的标准。一般的来说,图像处理的书籍总会或多或少的介绍一些图像分析和计算机视觉的知识,比如冈萨雷斯的数字图像处理。而计算机视觉的书籍基本上都会包括图像处理和图像分析,只是不会介绍的太详细。其实图像处理,图像分析和计算机视觉都可以纳入到计算机视觉的范畴:图像处理-低层视觉(low level vision),图像分析-中间层视觉(middle level vision),计算机视觉-高层视觉(high level vision)。这是一般的计算机视觉或者机器视觉的划分方法。在本文中,仍然按照传统的方法把这个领域划分为图像处理,图像分析和计算机视觉。 3. 图像处理和计算机视觉开源库以及编程语言选择 目前在图像处理中有两种最重要的语言:c/c++和matlab。它们各有优点:c/c++比较适合大型的工程,效率较高,而且容易转成硬件语言,是工业界的默认语言之一。而matlab实现起来比较方便,适用于算法的快速验证,而且matlab有成熟的工具箱可以使用,比如图像处理工具箱,信号处理工具箱。它们有一个共同的特点:开源的资源非常多。在学术界matlab使用的非常多,很多作者给出的源代码都是matlab版本。最近由于OpenCV的兴起和不断完善,c/c++在图像处理中的作用越来越大。总的来说,c/c++和matlab都必须掌握,最好是精通,当然侧重在c/c++上对找工作会有很大帮助。 至于开源库,个人非常推荐OpenCV,主要有以下原因: (1)简单易入手。opencv进入opencv2.x的时代后,使用起来越来越简单,接口越来越傻瓜化,越来越matlab化。只要会imread,imwrite,imshow和了解Mat的基本操作就可以开始入手了。 (2)Opencv有一堆图像处理和计算机视觉的大牛在维护,bug在逐步减少,每个新的版本都会带来不同的惊喜。而且它已经或者逐步在移植到不同的平台,并提供了对Python的很好的支持。 (3)在Opencv上可以尝试各种最新以及成熟的技术,而不需要自己从头去写,比如人脸检测(Harr,LBP),DPM(Latent SVM),高斯背景模型,特征检测,聚类,hough变换等等。而且它还支持各种机器学习方法(SVM,NN,KNN,决策树,Boosting等),使用起来很简单。 (4)文档内容丰富,并且给出了很多示例程序。当然也有一些地方文档描述不清楚,不过看看代码就很清楚了。 (5)完全开源。可以从中间抠出任何需要的算法。 (6)从学校出来后,除极少数会继续在学术圈里,大部分还是要进入工业界。现在在工业界,c/c++仍是主流,很多公司都会优先考虑熟悉或者精通opencv的。事实上,在学术界,现在opencv也大有取代matlab之势。以前的demo或者sourcecode,很多作者都愿意给出matlab版本的,然后别人再呼哧呼哧改成c版本的。现在作者干脆给出c/c++版本,或者自己集成到opencv中去,这样能快速提升自己的影响力。 如果想在图像处理和计算机视觉界有比较深入的研究,并且以后打算进入这个领域工作的话,建议把OpenCV作为自己的主攻方向。如果找工作的时候敢号称自己精通OpenCV的话,肯定可以找到一份满意的工作。 4. 本文的特点和结构,以及适合的对象 本文面向的对象是即将进入或者刚刚进入图像处理和计算机视觉领域的童鞋,可以在阅读书籍的同时参阅这些文献,能对书中提到的算法有比较深刻的理解。由于本文涉及到的范围比较广,如果能对计算机视觉的资深从业者也有一定的帮助,我将倍感欣慰。为了不至太误人子弟,每一篇文章都或多或少的看了一下,最不济也看了摘要(这句话实在整理之前写的,实际上由于精力有限,好多文献都只是大概扫了一眼,然后看了看google的引用数,一般在1000以上就放上来了,把这些文章细细品味一遍也是我近一两年之内的目标)。在成文的过程中,我本人也受益匪浅,希望能对大家也有所帮助。 由于个人精力和视野的关系,有一些我未涉足过的领域不敢斗胆推荐,只是列出了一些引用率比较高的文章,比如摄像机标定和立体视觉。不过将来,由于工作或者其他原因,这些领域也会接触到,我会逐步增减这些领域的文章。同时文章的挑选也夹带了一些个人的喜好,比如我个人比较喜欢low level方向的,尤其是IJCV和PAMI上面的文章,因此这方面也稍微多点,希望不要引起您的反感。如果有什么意见或者建议,欢迎mail我。文章和资源我都会在我的csdn blog和sina ishare同步更新。在此申明:这些论文的版权归作者及其出版社所有,请勿用于商业目的。 个人blog: http://blog.csdn.net/dcraw 新浪iask地址: http://iask.sina.com.cn/u/2252291285/ish?folderid=868438 本文的安排如下。第一部分是绪论。第二部分是图像处理中所需要用到的理论基础,主要是这个领域所涉及到的一些比较好的参考书籍。第三部分是计算机视觉中所涉及到的信号处理和模式识别文章。由于图像处理与图像分析太难区分了,第四部分集中讨论了它们。第五部分是计算机视觉部分。最后是小结。 图像处理与计算机视觉:基础,经典以及最近发展( 2 ) 图像处理与计算机视觉相关的书籍 1. 数学 我们所说的图像处理实际上就是数字图像处理,是把真实世界中的连续三维随机信号投影到传感器的二维平面上,采样并量化后得到二维矩阵。数字图像处理就是二维矩阵的处理,而从二维图像中恢复出三维场景就是计算机视觉的主要任务之一。这里面就涉及到了图像处理所涉及到的三个重要属性:连续性,二维矩阵,随机性。所对应的数学知识是高等数学(微积分),线性代数(矩阵论),概率论和随机过程。这三门课也是考研的三门课,构成了图像处理和计算机视觉最基础的数学基础。如果想要更进一步,就要到网上搜搜林达华推荐的数学数目了。 2. 信号处理 图像处理其实就是二维和三维信号处理,而处理的信号又有一定的随机性,因此经典信号处理和随机信号处理都是图像处理和计算机视觉中必备的理论基础。 2.1 经典信号处理 信号与系统 ( 第2版) Alan V.Oppenheim等著 刘树棠译 离散时间信号处理 ( 第2版) A.V.奥本海姆等著刘树棠译 数字信号处理:理论算法与实现 胡广书 (编者) 2.2 随机信号处理 现代信号处理 张贤达著 统计信号处理基础 : 估计与检测理论 Steven M.Kay 等著 罗鹏飞等译 自适应滤波器原理 ( 第4版) Simon Haykin著郑宝玉等译 2.3 小波变换 信号处理的小波导引 : 稀疏方法 ( 原书第3版) tephaneMalla著, 戴道清等译 2.4 信息论 信息论基础 ( 原书第2版) Thomas M.Cover等著 阮吉寿等译 3. 模式识别 Pattern Recognition and MachineLearning Bishop , Christopher M. Springer 模式识别 ( 英文版) (第4版) 西奥多里德斯著 Pattern Classification (2ndEdition) Richard O. Duda 等著 Statistical Pattern Recognition , 3rd Edition Andrew R. Webb 等著 模式识别 ( 第3版) 张学工著 4. 图像处理与计算机视觉的书籍推荐 图像处理,分析与机器视觉 第三版Sonka等著 艾海舟等译 ※ Image Processing, Analysis and MachineVision 这本书是图像处理与计算机视觉里面比较全的一本书了,几乎涵盖了图像视觉领域的各个方面。中文版的个人感觉也还可以,值得一看。 数字图像处理 第三版 冈萨雷斯等著 ※ Digital Image Processing 数字图像处理永远的经典,现在已经出到了第三版,相当给力。我的导师曾经说过,这本书写的很优美,对写英文论文也很有帮助,建议购买英文版的。 计算机视觉:理论与算法 RichardSzeliski 著 Computer Vision: Theory andAlgorithm 微软的Szeliski写的一本最新的计算机视觉著作。内容非常丰富,尤其包括了作者的研究兴趣,比如一般的书里面都没有的Image Stitching和Image Matting等。这也从另一个侧面说明这本书的通用性不如Sonka的那本。不过作者开放了这本书的电子版,可以有选择性的阅读。 Multiple View Geometry in Computer Vision 第二版Harley等著 ※ 引用达一万多次的经典书籍了。第二版到处都有电子版的。第一版曾出过中文版的,后来绝版了。网上也可以找到电子版。 计算机视觉:一种现代方法 DAForsyth 等著 Computer Vision: A ModernApproach MIT 的经典教材。虽然已经过去十年了,还是值得一读。 第二版已经在今年(2012年)出来了,在iask上可以找到非常清晰的版本,将近800页,补充了很多内容。期待影印版。 Machine vision: theory,algorithms, practicalities 第三版 Davies著 为数不多的英国人写的书,偏向于工业。 Computer Vision:Algorithmsand Applications Richard Szeliszi 著 ※ 数字图像处理 第四版 Pratt著 Digital Image Processing 写作风格独树一帜,也是图像处理领域很不错的一本书。网上也可以找到非常清晰的电子版。 5 小结 罗嗦了这么多,实际上就是几个建议: (1)基础书千万不可以扔,也不能低价处理给同学或者师弟师妹。不然到时候还得一本本从书店再买回来的。钱是一方面的问题,对着全新的书看完全没有看自己当年上过的课本有感觉。 (2)遇到有相关的课,果断选修或者蹭之,比如随机过程,小波分析,模式识别,机器学习,数据挖掘,现代信号处理甚至泛函。多一些理论积累对将来科研和工作都有好处。 (3)资金允许的话可以多囤一些经典的书,有的时候从牙缝里面省一点都可以买一本好书。不过千万不要像我一样只囤不看。 图像处理与计算机视觉:基础,经典以及最近发展( 3 ) 计算机视觉中的信号处理与模式识别 从本章开始,进入本文的核心章节。一共分三章,分别讲述信号处理与模式识别,图像处理与分析以及计算机视觉。与其说是讲述,不如说是一些经典文章的罗列以及自己的简单点评。与前一个版本不同的是,这次把所有的文章按类别归了类,并且增加了很多文献。分类的时候并没有按照传统的分类方法,而是划分成了一个个小的门类,比如SIFT,Harris都作为了单独的一类,虽然它们都可以划分到特征提取里面去。这样做的目的是希望能突出这些比较实用且比较流行的方法。为了以后维护的方法,按照字母顺序排的序。 本章的下载地址在: http://iask.sina.com.cn/u/2252291285/ish?folderid=868770 1. Boosting Boosting 是最近十来年来最成功的一种模式识别方法之一,个人认为可以和SVM并称为模式识别双子星。它真正实现了“三个臭皮匠,赛过诸葛亮”。只要保证每个基本分类器的正确率超过50%,就可以实现组合成任意精度的分类器。这样就可以使用最简单的线性分类器。Boosting在计算机视觉中的最成功的应用无疑就是Viola-Jones提出的基于Haar特征的人脸检测方案。听起来似乎不可思议,但Haar+Adaboost确实在人脸检测上取得了巨大的成功,已经成了工业界的事实标准,并且逐步推广到其他物体的检测。 Rainer Lienhart 在2002 ICIP发表的这篇文章是Haar+Adaboost的最好的扩展,他把原始的两个方向的Haar特征扩展到了四个方向,他本人是OpenCV积极的参与着。现在OpenCV的库里面实现的Cascade Classification就包含了他的方法。这也说明了盛会(如ICIP,ICPR,ICASSP)也有好文章啊,只要用心去发掘。 A Decision-Theoretic Generalization of on-Line Learning and an Application toBoosting Boosting the margin A new explanation for the effectiveness of voting methods Empirical Analysis of Detection Cascades of Boosted Classifiers forRapid ObjectDetection The Boosting Approach to Machine Learning An Overview Robust Real-time Face Detection 2. Clustering 聚类主要有K均值聚类,谱聚类和模糊聚类。在聚类的时候如果自动确定聚类中心的数目是一个一直没有解决的问题。不过这也很正常,评价标准不同,得到的聚类中心数目也不一样。不过这方面还是有一些可以参考的文献,在使用的时候可以基于这些方法设计自己的准则。关于聚类,一般的模式识别书籍都介绍的比较详细,不过关于cluster validity讲的比较少,可以参考下面的文章看看。 Unsupervised Optimal Fuzzy Clustering A validity measure for fuzzy clustering On cluster validity for the fuzzy c-means model Some New Indexes of Cluster Validity Data Clustering A Review On Clustering Validation Techniques Estimating the number of clusters in a dataset via the Gap statistic On Spectral Clustering A stability based method for discovering structure in clustered data A tutorial on spectral clustering 3. Compressive Sensing 最近大红大紫的压缩感知理论。 Compressed Sensing An Introduction to Compressive Sampling Structured Compressed Sensing From Theory to Applications 4. Decision Trees 对决策树感兴趣的同学这篇文章是非看不可的了。 Introduction to Decision Trees 5. Dynamical Programming 动态规划也是一个比较使用的方法,这里挑选了一篇PAMI的文章以及一篇Book Chapter using dynamic programming for solving variational problems in vision Dynamic Programming 6. Expectation Maximization EM 是计算机视觉中非常常见的一种方法,尤其是对参数的估计和拟合,比如 高斯混合模型 。EM和GMM在Bishop的PRML里单独的作为一章,讲的很不错。关于EM的tutorial,网上也可以搜到很多。 Maximum likelihood from incomplete data via the EM algorithm The Expectation-Maximzation Algorithm 7. Graphical Models 伯克利的乔丹大仙的Graphical Model,可以配合这Bishop的PRML一起看。 An Introduction to Variational Methods for Graphical Models 8. Hidden Markov Model HMM 在语音识别中发挥着巨大的作用。在信号处理和图像处理中也有一定的应用。最早接触它是跟小波和检索相关的,用HMM来描述小波系数之间的相互关系,并用来做检索。这里提供一篇1989年的经典综述,几篇HMM在小波,分割,检索和纹理上的应用以及一本比较早的中文电子书,现在也不知道作者是谁,在这里对作者表示感谢。 A tutorial on hidden markov models and selected applications in speechrecognition Wavelet-based statistical signal processing using hidden Markov models Multiscale image segmentation using wavelet-domain hidden Markov models Rotation invariant texture characterization and retrieval using steerablewavelet-domain hiddenMarkov models Wavelet-based texture analysis and synthesis using hidden Markov models HmmChinese book.pdf 9. Independent Component Analysis 同PCA一样, 独立成分分析 在计算机视觉中也发挥着重要的作用。这里介绍两篇综述性的文章,最后一篇是第二篇的TR版本,内容差不多,但比较清楚一些。 Independent Component Analysis A Tutorial Independent component analysis algorithms and applications Independent Component Analysis Algorithms and Applications 10. Information Theory 计算机视觉中的信息论。这方面有一本很不错的书Information Theoryin Computer Vision and Pattern Recognition。这本书有电子版,如果需要用到的话,也可以参考这本书。 An Information-Maximization Approach to Blind Separation and BlindDeconvolution An information theory perspective on computational vision 11. Kalman Filter 这个话题在张贤达老师的现代信号处理里面讲的比较深入,还给出了一个有趣的例子。这里列出了Kalman的最早的论文以及几篇综述,还有Unscented Kalman Filter。同时也有一篇Kalman Filter在跟踪中的应用以及两本电子书。 A New Approach to Linear Filtering and Prediction Problems Kalman Least-squares estimation_from Gauss to Kalman A New Extension of the Kalman Filter to Nonlinear System The Unscented Kalman Filter for Nonlinear Estimation An Introduction to the Kalman Filter_full A Study of the Kalman Filter applied to Visual Tracking 12. Pattern Recognition and MachineLearning 模式识别名气比较大的几篇综述 Statistical pattern recognition a review An Introduction to Biometric Recognition Machine Learning in Medical Imaging 13. Principal Component Analysis 著名的PCA,在特征的表示和特征降维上非常有用。 PCA versus LDA Nonlinear component analysisas a kernel eigenvalue problem A Tutorial on Principal Component Analysis Two-dimensional PCA a new approach to appearance-based facerepresentation and recognition A Tutorial on Principal Component Analysis Robust Principal Component Analysis Singular Value Decomposition and Principal Component Analysis 14. Random Forest 随机森林 Random Forests 15. RANSAC 随机抽样一致性方法,与传统的最小 均方误差 等完全是两个路子。在Sonka的书里面也有提到。 Performance Evaluation of RANSAC Family 16. Singular Value Decomposition 对于非方阵来说,就是SVD发挥作用的时刻了。一般的模式识别书都会介绍到SVD。这里列出了K-SVD以及一篇BookChapter K-SVD An Algorithm for Designing Overcomplete Dictionaries for SparseRepresentation Singular Value Decomposition and Principal Component Analysis 17. Sparse Representation 这里主要是Proceeding of IEEE上的几篇文章 Robust Face Recognition via Sparse Representation Image Decomposition and Separation Using Sparse Representations AnOverview Dictionaries for Sparse Representation Modeling It's All About the Data Matrix Completion With Noise On the Role of Sparse and Redundant Representations in Image Processing Sparse Representation for Computer Vision and Pattern Recognition Directionary Learning 18. Support Vector Machines A Tutorial on Support Vector Machines for Pattern Recognition LIBSVM A Library for Support Vector Machines 19. Wavelet 在小波变换之前,时频分析的工具只有傅立叶变换。众所周知,傅立叶变换在时域没有分辨率,不能捕捉局部频域信息。虽然短时傅立叶变换克服了这个缺点,但只能刻画恒定窗口的频率特性,并且不能很好的扩展到二维。小波变换的出现很好的解决了时频分析的问题,作为一种多分辨率分析工具,在图像处理中得到了极大的发展和应用。在小波变换的发展过程中,有几个人是不得不提的,Mallat, Daubechies,Vetteri, M.N.Do, Swelden,Donoho。Mallat和Daubechies奠定了第一代小波的框架,他们的著作更是小波变换的必读之作,相对来说,小波十讲太偏数学了,比较难懂。而Mallat的信号处理的小波导引更偏应用一点。Swelden提出了第二代小波,使小波变换能够快速方便的实现,他的功劳有点类似于FFT。而Donoho,Vetteri,Mallat及其学生们提出了Ridgelet, Curvelet,Bandelet,Contourlet等几何小波变换,让小波变换有了方向性,更便于压缩,去噪等任务。尤其要提的是M.N.Do,他是一个越南人,得过IMO的银牌,在这个领域著作颇丰。我们国家每年都有5个左右的IMO金牌,希望也有一两个进入这个领域,能够也让我等也敬仰一下。而不是一股脑的都进入金融,管理这种跟数学没有多大关系的行业,呵呵。很希望能看到中国的陶哲轩,中国的M.N.Do。 说到小波,就不得不提JPEG2000。在JPEG2000中使用了Swelden和Daubechies提出的用提升算法实现的9/7小波和5/3小波。如果对比JPEG和JPEG2000,就会发现JPEG2000比JPEG在性能方面有太多的提升。本来我以为JPEG2000的普及只是时间的问题。但现在看来,这个想法太Naive了。现在已经过去十几年了,JPEG2000依然没有任何出头的迹象。不得不说,工业界的惯性力量太强大了。如果以前的东西没有什么硬伤的话,想改变太难了。不巧的是,JPEG2000的种种优点在最近的硬件上已经有了很大的提升。压缩率?现在动辄1T,2T的硬盘,没人太在意压缩率。渐进传输?现在的网速包括无线传输的速度已经相当快了,渐进传输也不是什么优势。感觉现在做图像压缩越来越没有前途了,从最近的会议和期刊文档也可以看出这个趋势。不管怎么说,JPEG2000的Overview还是可以看看的。 A theory for multiresolution signal decomposition__the waveletrepresentation Image Representation using 2D Gabor Wavelet FACTORING WAVELET TRANSFORMSIN TO LIFTING STEPS The Lifting Scheme_ A Construction Of Second Generation Wavelets The JPEG2000 still image coding system_ an overview The curvelet transform for image denoising Gray and color imagecontrast enhancement by the curvelet transform Mathematical Properties of the jpeg2000 wavelet filters The finite ridgelet transform for image representation Sparse Geometric Image Representations With Bandelets The Contourlet Transform_ An Efficient Directional Multiresolution ImageRepresentation The Curvelet Transform 图像处理与计算机视觉:基础,经典以及最近发展( 4 ) 图像处理与分析 本章主要讨论图像处理与分析。虽然后面计算机视觉部分的有些内容比如特征提取等也可以归结到图像分析中来,但鉴于它们与计算机视觉的紧密联系,以及它们的出处,没有把它们纳入到图像处理与分析中来。同样,这里面也有一些也可以划归到计算机视觉中去。这都不重要,只要知道有这么个方法,能为自己所用,或者从中得到灵感,这就够了。 本章的下载地址在: http://iask.sina.com.cn/u/2252291285/ish?folderid=868771 1.Bilateral Filter Bilateral Filter 俗称双边滤波器是一种简单实用的具有保持边缘作用的平缓滤波器,由Tomasi等在1998年提出。它现在已经发挥着重大作用,尤其是在HDR领域。 BilateralFiltering for Gray and Color Images AdaptiveBilateral Filter for Sharpness Enhancement and Noise Removal 2.Color 如果对颜色的形成有一定的了解,能比较深刻的理解一些算法。这方面推荐冈萨雷斯的数字图像处理中的相关章节以及Sharma在Digital Color Imaging Handbook中的第一章“Colorfundamentals for digital imaging”。跟颜色相关的知识包括Gamma,颜色空间转换,颜色索引以及肤色模型等,这其中也包括著名的EMD。 ColorIndexing TheEarthMover's Distance as a Metric for Image Retrieval Colorinvariance StatisticalColor Models with Application to Skin Detection A review ofRGBcolor spaces A surveyofskin-color modeling and detection methods Gamma.pdf GammaFAQ.pdf 3.Compressionand Encoding 个人以为图像压缩编码并不是当前很热的一个话题,原因前面已经提到过。这里可以看看一篇对编码方面的展望文章 Trendsandperspectives in image and video coding 4.ContrastEnhancement 对比度增强一直是图像处理中的一个恒久话题,一般来说都是基于直方图的,比如 直方图均衡化 。冈萨雷斯的书里面对这个话题讲的比较透彻。这里推荐几篇个人认为不错的文章。 Vision andtheAtmosphere Gray andcolorimage contrast enhancement by the curvelet transform Gray-levelgrouping (GLG) an automatic method for optimized imagecontrastenhancement-part II Gray-levelgrouping (GLG) an automatic method for optimized imagecontrastEnhancement-part I TransformCoefficient Histogram-Based Image Enhancement Algorithms UsingContrast Entropy AHistogramModification Framework and Its Application for Image ContrastEnhancement 5.Deblur (Restoration) 图像恢复或者图像去模糊一直是一个非常难的问题,尤其是盲图像恢复。港中文的jiaya jia老师在这方面做的不错,他在主页也给出了exe。这方面的内容也建议看冈萨雷斯的书。这里列出了几篇口碑比较好的文献,包括古老的Richardson-Lucy方法,几篇盲图像恢复的综述以及最近的几篇文章,尤以Fergus和Jiaya Jia的为经典。 Bayesian-BasedIterative Method of Image Restoration an iterativetechniquefor the rectification of observed distributions Iterativemethods for image deblurring BlindImageDeconvolution Digitalimagerestoration DigitalImageReconstruction - Deblurring and Denoising RemovingCamera Shake from a Single Photograph High-quality Motion Deblurring from a Single Image Richardson-Lucy Deblurring for Scenes under a Projective Motion Path 6.Dehazing and Defog 严格来说去雾化也算是图像对比度增强的一种。这方面最近比较好的工作就是He kaiming等提出的Dark Channel方法。这篇论文也获得了2009的 CVPR 最佳论文奖。2003年的广东高考状元已经于2011年从港中文博士毕业加入MSRA(估计当时也就二十五六岁吧),相当了不起。 SingleImage Dehazing SingleImageHaze Removal Using Dark Channel Prior SingleImageHaze Removal Using Dark Channel Prior 7.Denoising 图像去噪也是图像处理中的一个经典问题,在数码摄影中尤其重要。主要的方法有基于小波的方法和基于偏微分方程的方法。 Imageselective smoothing and edge detection by nonlinear diffusion. II Imageselective smoothing and edge detection by nonlinear diffusion Nonlineartotalvariation based noise removal algorithms Signalandimage restoration using shock filters and anisotropic diffusion De-noisingbysoft-thresholding Orientationdiffusions Adaptivewaveletthresholding for image denoising and compression Fourth-orderpartial differential equations for noise removal Denoising throughwavelet shrinkage TheCurveletTransform for Image Denoising Noise removalusingfourth-order partial differential equation with applications to medicalmagneticresonance images in space and time AutomaticEstimation and Removal of Noise from a Single Image IsDenoisingDead 8.Edge Detection 边缘检测也是图像处理中的一个基本任务。传统的边缘检测方法有基于 梯度算子 ,尤其是 Sobel 算子 ,以及经典的Canny边缘检测。到现在,Canny边缘检测及其思想仍在广泛使用。关于Canny算法的具体细节可以在Sonka的书以及canny自己的论文中找到,网上也可以搜到。最快最直接的方法就是看OpenCV的源代码,非常好懂。在边缘检测方面,Berkeley的大牛J Malik和他的学生在2004年的PAMI提出的方法效果非常好,当然也比较复杂。在复杂度要求不高的情况下,还是值得一试的。MIT的Bill Freeman早期的代表作Steerable Filter在边缘检测方面效果也非常好,并且便于实现。这里给出了几篇比较好的文献,包括一篇最新的综述。边缘检测是图像处理和计算机视觉中任何方向都无法逃避的一个问题,这方面研究多深都不为过。 theory ofedgedetection findedge AComputational Approach to Edge Detection Scale-spaceand edge detection using anisotropic diffusion The designanduse of steerable filters Multiresolutionedge detection techniques Optimaledgedetection in two-dimensional images LocalScaleControl for Edge Detection and Blur Estimation Statisticaledge detection_ learning and evaluating edge cues EdgeDetectionRevisited Designofsteerable filters for feature detection using canny-like criteria LearningtoDetect Natural Image Boundaries Using Local Brightness, Color, and TextureCues Edge andlineoriented contour detection State of the art 9.Graph Cut 基于图割的图像分割算法。在这方面没有研究,仅仅列出几篇引用比较高的文献。这里又见J Malik,当然还有华人杰出学者Jianbo Shi,他的主页非常搞笑,在醒目的位置标注 Do not flyChina Eastern Airlines ... 看来是被坑过,而且坑的比较厉害。这个领域,俄罗斯人比较厉害。 Normalizedcuts and image segmentation Fastapproximate energy minimization via graph cuts Whatenergyfunctions can be minimized via graph cuts 10.HoughTransform 虽然霍夫变换可以扩展到广义霍夫变换,但最常用的还是检测圆和直线。这方面同样推荐看OpenCV的源代码,一目了然。Matas在2000年提出的PPHT已经集成到OpenCV中去了。 A Surveyofthe Hough Transform A Comparativestudyof Hough transform methods for circle finding Shapesrecognition using the straight line Hough transform_ theory andgeneralization Extractionofline features in a noisy image RobustDetection of Lines Using the Progressive Probabilistic Hough Transform 11.Image Interpolation 图像插值,偶尔也用得上。一般来说,双三次也就够了 Interpolationrevisited 12.Image Matting 也就是最近,我才知道这个词翻译成中文是抠图,比较难听,不知道是谁开始这么翻译的。没有研究,请看文章以及 Richard Szeliski 的相关章节。以色列美女Levin在这方面有两篇PAMI。 Image andVideoMatting A Survey AClosed-FormSolution to Natural Image Matting SpectralMatting 13.Image Modeling 图像的统计模型。这方面有一本专门的著作Natural Image Statistics The statisticsofnatural images On AdvancesinStatistical Modeling of Natural Images FieldsofExperts Modelingmultiscale subbands of photographic images with fields of Gaussianscalemixtures 14.Image Quality Assessment 在图像质量评价方面,Bovik是首屈一指的。这位老师也很有意思,作为编辑出版了很多书。他也是IEEE的Fellow Imagequalityassessment from error visibility to structural similarity blindimagequality assessment From Natural Scene Statistics to Perceptual Quality 15.Image Registration 图像配准最早的应用在医学图像上,在图像融合之前需要对图像进行配准。在现在的计算机视觉中,配准也是一个需要理解的概念,比如跟踪,拼接等。在KLT中,也会涉及到配准。这里主要是综述文献。 Image matchingasa diffusion process A MethodforRegistration of 3-D shapes a survey ofimageregistration techniques A surveyofmedical image registration Imageregistration methods a survey Mutual-Information-BasedRegistration of Medical Survey Hairisregistration 16.Image Retrieval 图像检索曾经很热,在2000年之后似乎消停了一段时间。最近各种图像的不变性特征提出来之后,再加上互联网搜索的商业需求,这个方向似乎又要火起来了,尤其是在工业界。这仍然是一个非常值得关注的方面。而且图像检索与目标识别具有相通之处,比如特征提取和特征降维。这方面的文章值得一读。在最后给出了两篇Book chapter,其中一篇还是中文的。 Content-basedimage retrieval at the end of the early years PicToSeekCombining Color and Shape Invariant Features for Image Retrieval Content-BasedImageRetrieval Systems A Survey Content-Based ImageRetrieval-LiteratureSurvey PlantImageRetrieval Using Color,Shape and Texture Features AMultimediaRetrieval Framework Based on Semi-Supervised Ranking and RelevanceFeedback CBIR Chinese fundament of cbir 17.Image Segmentation 图像分割,非常基本但又非常难的一个问题。建议看Sonka和冈萨雷斯的书。这里给出几篇比较好的文章,再次看到了J Malik。他们给出了源代码和测试集,有兴趣的话可以试试。 EfficientGraph-Based Image Segmentation Imagesegmentation evaluation A survey of unsupervised methods ContourDetection and Hierarchical Image Segmentation 18.Level Set 大名鼎鼎的水平集,解决了Snake固有的缺点。Level set的两位提出者Sethian和Osher最后反目,实在让人遗憾。个人以为,这种方法除了迭代比较费时,在真实场景中的表现让人生疑。不过,2008年ECCV上的PWP方法在结果上很吸引人。在重初始化方面,Chunming Li给出了比较好的解决方案 Shapemodelingwith front propagation_ a level set approach LevelSetMethods_ An Overview and Some Recent Results Geodesicactive regions and level set methods for motion estimation and tracking A ReviewofStatistical Approaches to Level Set Segmentation RobustReal-TimeVisual Tracking using Pixel-Wise Posteriors DistanceRegularized Level Set Evolution and its Application to ImageSegmentation 19.Pyramid 其实小波变换就是一种金字塔分解算法,而且具有无失真重构和非冗余的优点。Adelson在1983年提出的Pyramid优点是比较简单,实现起来比较方便。 TheLaplacianPyramid as a Compact Image Code 20. Radon Transform Radon 变换也是一种很重要的变换,它构成了图像重建的基础。关于图像重建和radon变换,可以参考章毓晋老师的书,讲的比较清楚。 Imagerepresentation via a finite Radon transform Thefastdiscrete radon transform I theory Generalisedfinite radon transform for N ×N images 21.Scale Space 尺度空间滤波在现代不变特征中是一个非常重要的概念,有人说SIFT的提出者Lowe是不变特征之父,而Linderburg是不变特征之母。虽然尺度空间滤波是Witkin最早提出的,但其理论体系的完善和应用还是Linderburg的功劳。其在1998年IJCV上的两篇文章值得一读,不管是特征提取方面还是边缘检测方面。 Scale-spacefiltering Scale-Spacefor Discrete Signals Scale-spacetheoryA basic tool for analysing structures at different scales EdgeDetectionand Ridge Detection with Automatic Scale Selection FeatureDetection with Automatic Scale Selection 22. Snake 活动轮廓模型,改变了传统的图像分割的方法,用能量收缩的方法得到一个统计意义上的能量最小(最大)的边缘。 SnakesActiveContour Models deformablemodelin medical image A Survey geodesicactive contour Snakes,shapes,and gradient vector flow Geodesicactivecontours and level sets for the detection and tracking of moving objects Activecontourswithout edges 23. Super Resolution 超分辨率分析。对这个方向没有研究,简单列几篇文章。其中Yang Jianchao的那篇在IEEE上的下载率一直居高不下。 Example-BasedSuper-Resolution Super-Resolution Image Reconstruction A Technical Overview Super-Resolutionfrom a Single Image ImageSuper-Resolution Via Sparse Representation 24. Thresholding 阈值分割是一种简单有效的图像分割算法。这个topic在冈萨雷斯的书里面讲的比较多。这里列出OTSU的原始文章以及一篇不错的综述。 OTSUAthreshold selection method from gray-level histograms A FastAlgorithmfor Multilevel Thresholding Surveyoverimage thresholding techniques and quantitative performance evaluation 25. Watershed 分水岭算法是一种非常有效的图像分割算法,它克服了传统的阈值分割方法的缺点,尤其是Marker-Controlled Watershed,值得关注。Watershed在冈萨雷斯的书里面讲的比较详细。 Watershedsindigital spaces an efficient algorithm based on immersion simulations TheWatershedTransform Definitions, Algorithms and Parallelizat on Strategies 图像处理与计算机视觉:基础,经典以及最近发展( 5 ) 计算机视觉 这一章是计算机视觉部分,主要侧重在底层特征提取, 视频分析 ,跟踪,目标检测和识别方面等方面。对于自己不太熟悉的领域比如摄像机标定和立体视觉,仅仅列出上google上引用次数比较多的文献。有一些刚刚出版的文章,个人 非常喜欢 ,也列出来了。 本章的下载地址: http://iask.sina.com.cn/u/2252291285/ish?folderid=868772 1. Active Appearance Models 活动表观模型和活动轮廓模型基本思想来源Snake,现在在人脸三维建模方面得到了很成功的应用,这里列出了三篇最初最经典的文章。对这个领域有兴趣的可以从这 三篇文章 开始入手。 ActiveAppearance Models ActiveAppearance Models 2. Active Shape Models Active ShapeModels-Their Training and Application 3. Background modeling andsubtraction 背景建模一直是视频分析尤其是目标检测中的一项关键技术。虽然最近一直有一些新技术的产生,demo效果也很好,比如基于dynamical texture的方法。但最经典的还是Stauffer等在1999年和2000年提出的GMM方法,他们最大的贡献在于不用EM去做高斯拟合,而是采用了一种迭代的算法,这样就不需要保存很多帧的数据,节省了buffer。Zivkovic在2004年的ICPR和PAMI上提出了动态确定高斯数目的方法,把混合 高斯模型 做到了极致。这种方法效果也很好,而且易于实现。在OpenCV中有现成的函数可以调用。在背景建模大家族里,无参数方法(2000 ECCV)和Vibe方法也值得关注。 PfinderReal-Time Tracking of the Human Body Adaptivebackground mixture models for real-time tracking WallflowerPrinciples and Practice of Background Maintenance Non-parametricModel for Background Subtraction LearningPatterns of Activity Using Real-Time Tracking Backgroundand foreground modeling using nonparametric kernel density estimationforvisual surveillance Improvedadaptive Gaussian mixture model for background subtraction Recursiveunsupervised learning of finite mixture models Efficientadaptive density estimation per image pixel for the task ofbackgroundsubtraction ViBeAUniversal Background Subtraction Algorithm for Video Sequences 4. Bag of Words 词袋,在这方面暂时没有什么研究。列出三篇引用率很高的文章,以后逐步解剖之。 Video Google AText Retrieval Approach to Object Matching in Videos VisualCategorization with Bags of Keypoints Beyond bags offeatures Spatial pyramid matching for recognizing natural scenecategories 5. BRIEF BRIEF 是BinaryRobust Independent ElementaryFeatures的简称,是近年来比较受关注的特征描述的方法。ORB也是基于BRIEF的。 BRIEF BinaryRobust Independent Elementary Features ORBanefficient alternative to SIFT or SURF BRIEFComputing a Local Binary Descriptor Very Fast 6. Camera Calibration andStereoVision 非常不熟悉的领域。仅仅列出了十来篇重要的文献,供以后学习。 AComputational Theory of Human Stereo Vision Computationalvision and regularization theory Aversatilecamera calibration technique for high-accuracy 3D machine visionmetrologyusing off-the-shelf TV cameras and lenses ProbabilisticSolution of Ill-Posed Problems in Computational Vision Ill-PosedProblems in Early Vision KalmanFilter-based Algorithms for Estimating Depth from Image Sequences RelativeOrientation Usingvanishing points for camera calibration Cameraself-calibration Theory and experiments Atheory ofself-calibration of a moving camera Cameracalibration with distortion models and accuracy evaluation TheFundamental Matrix Theory, Algorithms, and Stability Analysis astereomatching algorithm with an adaptive window theory and experiment Flexiblecamera calibration by viewing a plane from unknown orientations Markertracking and hmd calibration for a video-based augmented realityconferencingsystem Aflexible newtechnique for camera calibration 7. Color and Histogram Feature 这里面主要来源于图像检索,早期的图像检测基本基于全局的特征,其中最显著的就是颜色特征。这一部分可以和前面的Color知识放在一起的。 Similarity ofcolor images IMAGERETRIEVALUSING COLOR AND SHAPE comparingimagesusing color coherence vectors ImageIndexingUsing Color Correlograms AnEfficientColor Representation for Image Retrieval Performanceevaluation of local colour invariants 8. Deformable Part Model 大红大热的DPM,在OpenCV中有一个专门的topic讲DPM和latent svm ADiscriminatively Trained, Multiscale, Deformable Part Model Cascade ObjectDetection with Deformable Part Models ObjectDetection with Discriminatively Trained Part-Based Models 9. Distance Transformations 距离变换,在OpenCV中也有实现。用来在二值图像中寻找种子点非常方便。 DistanceTransformations in Digital Images 2DEuclideanDistance Transform Algorithms A Comparative Survey 10. Face Detection 最成熟最有名的当属Haar+Adaboost NeuralNetwork-Based Face Detection Detectingfaces in images a survey FaceDetectionin Color Images RobustReal-Time Face Detection 11. Face Recognition 不熟悉,简单罗列之。 FaceRecognitionUsing Eigenfaces AutomaticAnalysis of Facial Expressions The State of the Art FaceRecognition ALiterature Survey Facerecognitionfrom a single image per person A survey Robust FaceRecognition via Sparse Representation 12. FAST 用机器学习的方法来提取角点,号称很快很好。 Machinelearning for high-speed corner detection Faster andBetter A Machine Learning Approach to Corner Detection 13. Feature Extraction 这里的特征主要都是各种不变性特征,SIFT,Harris,MSER等也属于这一类。把它们单独列出来是因为这些方法更流行一点。关于不变性特征,王永明与王贵锦合著的《 图像局部不变性特征与描述 》写的还不错。Mikolajczyk在2005年的PAMI上的文章以及2007年的综述是不错的学习材料。 Onthedetection of dominant points on digital curves SUSAN —A NewApproach to Low Level Image Processing MatchingWidely Separated Views Based on Affine Invariant Regions Scale Affine Invariant Interest Point Detectors Aperformanceevaluation of local descriptors AComparisonof Affine Region Detectors LocalInvariantFeature Detectors - A Survey Evaluation ofInterest Point Detectors and Feature Descriptors 14. Feature Matching LDAHashImproved Matching with Smaller Descriptors 15. Harris 虽然过去了很多年,Harris角点检测仍然广泛使用,而且基于它有很多变形。如果仔细看了这种方法,从直观也可以感觉到这是一种很稳健的方法。 Acombinedcorner and edge detector 16. Histograms of OrientedGradients HoG 方法也在OpenCV中实现了:HOGDescriptor。 Histograms ofOriented Gradients for Human Detection NavneetDalalThesis.pdf 17. Image Distance ComparingImages Using the Hausdorff Distance 18. Image Stitching 图像拼接,另一个相关的词是Panoramic。在Computer Vision: Algorithms and Applications一书中,有专门一章是讨论这个问题。这里的两面文章一篇是综述,一篇是这方面很经典的文章。 ImageAlignmentand Stitching A Tutorial AutomaticPanoramic Image Stitching using Invariant Features 19. KLT KLT 跟踪算法,基于Lucas-Kanade提出的配准算法。除了三篇很经典的文章,最后一篇给出了OpenCV实现KLT的细节。 AnIterative ImageRegistration Technique with an Application to Stereo Vision fullversion GoodFeaturesto Track Lucas-Kanade 20 Years On A Unifying Framework PyramidalImplementationof the Lucas Kanade Feature Tracker OpenCV 20. Local Binary Pattern LBP 。OpenCV的Cascade分类器也支持LBP,用来取代Haar特征。 Multiresolution gray-scale and rotation Invariant Texture ClassificationwithLocal Binary Patterns FaceRecognition with Local Binary Patterns FaceDescription with Local Binary Patterns Rotation-InvariantImage and Video Description With Local Binary PatternFeatures 21. Low-Level Vision 关于Low level vision的两篇很不错的文章 Ageneralframework for low level vision LearningLow-Level Vision 22. Mean Shift 均值漂移算法,在跟踪中非常流行的方法。Comaniciu在这个方面做出了重要的贡献。最后三篇,一篇是CVIU上的top download文章,一篇是最新的PAMI上关于Mean Shift的文章,一篇是OpenCV实现的文章。 Meanshift,mode seeking, and clustering Meanshift arobust approach toward feature space analysis Mean-shiftblob tracking through scale space Objecttracking using SIFT features and mean shift MeanShiftTrackers with Cross-Bin Metrics OpenCV ComputerVisionFace Tracking For Use in a Perceptual User Interface 23. MSER 这篇文章发表在2002年的BMVC上,后来直接录用到2004年的IVC上,内容差不多。MSER在Sonka的书里面也有提到。 Robust WideBaseline Stereo from Maximally Stable Extremal Regions MSERAuthorPresentation Robustwide-baseline stereo from maximally stable extremal regions AreMSERFeatures Really Interesting 24. Object Detection 首先要说的是第一篇文章的作者,Kah-Kay Sung。他是MIT的博士,后来到新加坡国立任教,极具潜力的一个老师。不幸的是,他和他的妻子都在2000年的新加坡空难中遇难,让人唏嘘不已。 http://en.wikipedia.org/wiki/Singapore_Airlines_Flight_006 最后一篇文章也是Fua课题组的,作者给出的demo效果相当好。 Example-basedlearning for view-based human face detection AStatistical Method for 3D Object Detection Applied to Faces and Cars Learning theStatistics of People in Images and Video Learning toDetect a Salient Object AReal-TimeDeformable Detector 25. Object Tracking 跟踪也是计算机视觉中的经典问题。粒子滤波,卡尔曼滤波,KLT,mean shift,光流都跟它有关系。这里列出的是传统意义上的跟踪,尤其值得一看的是2008的Survey和2003年的Kernelbased tracking。 Kernel-basedobject tracking TrackingPeople by Learning Their Appearance Object TrackingA Survey Segmentationand Tracking of Multiple Humans in Crowded Environments Hough Forestsfor Object Detection, Tracking, and Action Recognition Robust ObjectTracking with Online Multiple Instance Learning PWP3DReal-Time Segmentation and Tracking of 3D Objects 26. OCR 一个非常成熟的领域,已经很好的商业化了。 Historical reviewof OCR research and development Video OCR ASurvey andPractitioner's Guide 27. Optical Flow 光流法,视频分析所必需掌握的一种算法。 DetermineOptical Flow Performance ofoptical flow techniques TheComputationof Optical Flow TutorialComputing 2D and 3D Optical Flow Optical FlowEstimation LearningOptical Flow ADatabase andEvaluation Methodology for Optical Flow 28. Particle Filter 粒子滤波,主要给出的是综述以及1998 IJCV上的关于粒子滤波发展早期的经典文章。 CONDENSATION —ConditionalDensity Propagation for Visual Tracking Atutorial onparticle filters for online nonlinear non-Gaussian Bayesian tracking Particlefilters for positioning, navigation, and tracking particle filter 29. Pedestrian and Human detection 仍然是综述类,关于行人和人体的运动检测和动作识别。 Visualanalysis of human movement_ A survey ASurvey ofComputer Vision-Based Human Motion Capture Imagechangedetection algorithms a systematic survey asurvey ofavdances in vision based human motion capture Vision-basedhuman motion analysis An overview PedestrianDetection via Periodic Motion Analysis Asurvey ofskin-color modeling and detection methods Asurvey onvision-based human action recognition PedestrianDetection An Evaluation of the State of the Art 30. Scene Classification 当相机越来越傻瓜化的时候,自动场景识别就非常重要。这是比拼谁家的Auto功能做的比较好的时候了。 Modeling theShape of the Scene A Holistic Representation of the SpatialEnvelope Visual WordAmbiguity AThousandWords in a Scene EvaluatingColor Descriptors for Object and Scene Recognition CENTRIST AVisual Descriptor for Scene Categorization 31. Shadow Detection Detectingmoving shadows-- algorithms and evaluation 32. Shape 关于形状,主要是两个方面:形状的表示和形状的识别。形状的表示主要是从边缘或者区域当中提取不变性特征,用来做检索或者识别。这方面Sonka的书讲的比较系统。2008年的那篇综述在这方面也讲的不错。至于形状识别,最牛的当属J Malik等提出的Shape Context。 IMPROVED MOMENTINVARIANTS FOR SHAPE DISCRIMINATION PatternRecognition by Affine Moment Invariants IMAGERETRIEVALUSING COLOR AND SHAPE Shapematchingsimilarity measures and algorithms Shape matchingand object recognition using shape contexts Reviewof shaperepresentation and description techniques IntegralInvariants for Shape Matching A Surveyof ShapeFeature Extraction Techniques 33. SIFT 关于SIFT,实在不需要介绍太多,一万多次的引用已经说明问题了。SURF和PCA-SIFT也是属于这个系列。后面列出了几篇跟SIFT有关的问题。 Objectrecognition from local scale-invariant features Evaluation ofInterest Point Detectors Speeded-UpRobust Features (SURF) PCA-SIFT AMore Distinctive Representation for Local Image Descriptors DistinctiveImage Features from Scale-Invariant Keypoints ImprovingBag-of-Features for Large Scale Image Search SIFTflow DenseCorrespondence across Scenes and its Applications 34. SLAM SimultaneousLocalization and Mapping, 同步定位与建图。 SLAM 问题可以描述为: 机器人在未知环境中从一个未知位置开始移动,在移动过程中根据位置估计和地图进行自身定位,同时在自身定位的基础上建造增量式地图,实现机器人的自主定位和导航。 SimultaneousLocalization and Map-Building Using Active Vision MonoSLAMReal-TimeSingle Camera SLAM 35. Texture Feature 纹理特征也是物体识别和检索的一个重要特征集。 Texturalfeaturesfor image classification Statistical andstructural approaches to texture Texturefeatures for browsing and retrieval of image data Briefreview ofinvariant texture analysis methods ColorLocalTexture Features for Color Face Recognition 36. TLD Kadal 创立了TLD,跟踪学习检测同步进行,达到稳健跟踪的目的。他的两个导师也是大名鼎鼎,一个是发明MSER的Matas,一个是Mikolajczyk。他还创立了一个公司 TLDVisions.r.o . 这里给出了他的系列文章,最后一篇是刚出来的PAMI。 Onlinelearning ofrobust object detectors during unstable tracking P-NLearningBootstrapping Binary Classifiers by Structural Constraints FACE-TLDTRACKING-LEARNING-DETECTION APPLIED TO FACES Tracking-Learning-Detection 37. Video Surveillance 前面两个是两个很有名的视频监控系统,里面包含了很丰富的信息量,比如CMU的那个系统里面的背景建模算法也是相当简单有效的。最后一篇是比较近的综述。 ASystem forVideo Surveillance and Monitoring W4--real-timesurveillance of people and their activitie Theevolutionof video surveillance an overview 38. Viola-Jones Haar+Adaboost 的弱弱联手,组成了最强大的利器。在OpenCV里面有它的实现,也可以选择用LBP来代替Haar特征。 Rapid objectdetection using a boosted cascade of simple features RobustReal-timeFace Detection
个人主页 Alessandro Foi Andrea L. Bertozzi Antoni Buades Antonin Chambolle Jean-Luc Starck Jean-Michel Morel Yi Ma Stanley Osher Thomas Pock 公开数据集 The USC-SIPI Image Database 公开代码 Total Variation Denoising
首先可以把图像看成二维、三维或者更高维的信号,从这个意义上来说,图像处理是整个信号处理里面就业形势最好的,因为你不仅要掌握(一维)信号处理的基本知识,也要掌握图像处理(二维或者高维信号处理)的知识。其次,图像处理是计算机视觉和视频处理的基础,掌握好了图像处理的基本知识,就业时就可以向这些方向发展。目前的模式识别,大部分也都是图像模式识别。在实际应用场合,采集的信息很多都是图像信息,比如指纹、条码、人脸、虹膜、车辆等等。说到应用场合,千万不能忘了医学图像这一块,如果有医学图像处理的背景,去一些医疗器械公司或者医疗软件公司也是不错的选择。图像处理对编程的要求比较高,如果编程很厉害,当然就业也多了一个选择方向,并不一定要局限在图像方向。 下面谈谈我所知道的一些公司信息,不全,仅仅是我所了解到的或者我所感兴趣的,实际远远不止这么多。 搜索方向 基于内容的图像或视频搜索是很多搜索公司研究的热点。要想进入这个领域,必须有很强的编程能力,很好的图像处理和模式识别的背景。要求高待遇自然就不错,目前这方面的代表公司有微软、google、yahoo和百度,个个鼎鼎大名。 医学图像方向 目前在医疗器械方向主要是几个大企业在竞争,来头都不小,其中包括Simens、GE、飞利浦和柯达,主要生产CT和MRI等医疗器材。由于医疗器械的主要功能是成像,必然涉及到对图像的处理,做图像处理的很有机会进入这些公司。它们在国内都设有研发中心,simens的在上海和深圳,GE和柯达都在上海,飞利浦的在沈阳。由于医疗市场是一个没有完全开发的市场,而一套医疗设备的价格是非常昂贵的,所以在这些地方的待遇都还可以,前景也看好。国内也有一些这样的企业比如深圳安科和迈瑞 计算机视觉和模式识别方向 我没去调研过有哪些公司在做,但肯定不少,比如指纹识别、人脸识别、虹膜识别。还有一个很大的方向是车牌识别,这个我倒是知道有一个公司高德威智能交通似乎做的很不错的样子。目前视频监控是一个热点问题,做跟踪和识别的可以在这个方向找到一席之地。 上海法视特位于上海张江高科技园区,在视觉和识别方面做的不错。北京的我也知道两个公司:大恒和凌云,都是以图像作为研发的主体。 视频方向 一般的高校或者研究所侧重在标准的制定和修改以及技术创新方面,而公司则侧重在编码解码的硬件实现方面。一般这些公司要求是熟悉或者精通MPEG、H.264或者AVS,选择了这个方向,只要做的还不错,基本就不愁饭碗。由于这不是我所感兴趣的方向,所以这方面的公司的信息我没有收集,但平常在各个bbs或者各种招聘网站经常看到。 我所知道的两个公司:诺基亚和pixelworks 其他 其实一般来说,只要涉及到成像或者图像的基本都要图像处理方面的人。比方说一个成像设备,在输出图像之前需要对原始图像进行增强或者去噪处理,存储时需要对图像进行压缩,成像之后需要对图像内容进行自动分析,这些内容都是图像处理的范畴。下面列举一些与图像有关或者招聘时明确说明需要图像处理方面人才的公司: 上海豪威集成电路有限公司( www.ovt.com.cn ) 中芯微 摩托罗拉上海研究院 威盛(VIA) 松下 索尼 清华同方 三星 所有与图像(静止或者运动图像)有关的公司都是一种选择。比如数码相机、显微镜成像、超声成像、工业机器人控制、显示器、电视、遥感等等,都可以作为求职方向。 要求: 1、外语。如果进外企,外语的重要性不言而喻。一般外企的第一轮面试都是英语口语面试。 2、编程。这方面尤以C++为重,很多公司的笔试都是考c++知识。 3、专业水平。如果要找专业相关的工作,研究生期间的研究经历和发表的论文就显的比较重要。 4、知识面的宽度。我觉得在研究生期间,除了做好自己的研究方向之外,扩宽一下知识面也有很大的帮助,当然这个知识面指的是图像处理、计算机视觉和模式识别,知识面越宽,就业时的选择就会越多。 图像处理方向毕业的就业面非常广,而且待遇在应届生应该是中上等。其实还是一句话,能力决定一切。只要研究生三年没有白过,根本不愁找不到好工作。祝所有正在读研或者即将读研的朋友将来都能有一份满意的工作。 我说点不好的 呵呵 版主的说法我同意都是正面的 反面的来说:现在大学和研究机构做图象的越来越多了,这里面老板自己懂图象的不知道有多少?!老板不懂,影响还是很大的 多数做图象的是用MATLAB,用别人的代码(如小波)。在研究生三年学好C++毕业的有多少?在公司C++是重要的。 图象其实就是信号处理,除了本科是学信号的以外,信号与系统、数字信号处理是一定要学好的,那相应的数学方面的概率,多元统计,甚至泛函也要了解。 外语的基本要求是看懂英文文献(不一定全看懂),相应的英文书。去外企做研发,这是必备的。然后是口语和听力。 说这些不是波冷水,希望大家了解清楚。 Compared to the number of jobs available each year in the imaging soceity, the people who are majoring on it are way too much. I have to say most of the people who studied the this area were not end up with working on this area anymore. The most important thing here is to understand image processing, it requires a broad level of knowledge including, some math (algrebra, statistics, PDE), dsp, pattern recognition, programming skills... It is all these background skills will find you a job, so prepare to have a deep understanding on all these areas related to image processing 我也是学模式识别的,但是研究方向是遥感图像处理和识别.总的来说这个方向是比较专,但也是目前图像处理中比较难做的一个方向,因为遥感图像的复杂性超过我们所见过的任何图像. 其实谈到就业问题,我觉得如果研究方向比较适合,特别是读研期间能到斑竹谈的那些牛比的公司实习,了解企业真正需要的方向可能做起来有目标性. 顺便提下:高德威公司还是不要考虑,因为本人在毕业面试过程中,虽然面试的人力资源人员很友善,但是通过他们老板写的一些文章可以发现他们还是一个比较自恋和自大的公司. 楼主是好人 不过此文更多是安慰 新手不可太当真 衡量专业好坏的标准有两个:应用前景和技术门槛 个人觉得图像处理应用前景一般,比通信,计算机差远了,而技术门槛,相信不是新手都清楚,比微波之类低不少 总的来说图像方向就业一般,在it业算较冷得,特别是模式识别,人工智能之类,看起来高深邪乎,其实就是博士都不好找工作(亲身所见) 1)说到图像处理比通信差,很大部分的原因是当前行业背景,但通信真正的研发在中国又有多少,我的朋友中很多做工程的,况且现在在通信领域,很大的一个难点,也是多媒体通信。 2)说到比计算机差,我觉得这与你怎么看待计算机专业有关,有人觉得是基础,是工具,有人觉得是专业。况且计算机那边,现在研究图像的也不少。 3)再者,说微波,RFID等入门难,但要做精又谈何容易,而且兴趣真的很重要,没有兴趣,再有前景的专业,你也不一定能做好,还有女生并不适合搞这个,就业时,单位一般会暗示。另外,就业面也较窄,好公司真的难进,找工的时候,真的很郁闷,特别对女生。或许将来很大发展前途,这个另当别论。 4)说回图像处理,我觉得还是较中肯的,略有好的嫌疑,关键还是在读研的时候能把方向做宽(一般做图像处理,需要何模式识别等相结合,拓宽知识面是必要的,在真正做研究的时候,也发现是必须的),研究点做深入,注重实现能力、创新能力和学习能力,通过论文。多培养自己的材料组织提炼能力,锻炼逻辑思维。如果真的能做到三年光阴不虚度,找工应该不是问题,到时真正要考虑的是定位问题。 5)当然,最后,找工的时候,包装是一种技巧,整合是一种需要。 我觉得做图像处理还是很有前途的。 有做图像三维重建的来找我,我们公司做医疗影像的。 可以跟我Email联系: yalee@sina.com 作图像处理方面的研究工作,最重要的两个问题:其一是要把握住国际上最前 沿的内容;其二是所作工作要具备很高的实用背景。解决第一个问题的办法就 是找出这个方向公认最牛的几个超级大拿(看看他们都在作什么)和最权威的 出版物(阅读上面最新的文献),解决第二个问题的办法是你最好能够找到一个 实际应用的项目,边做边写文章。 做好这几点的途径之一就是充分利用网络资源,特别是权威网站和大拿们的个人主页。下面是我收集的一些资源,希望对大家有用。(这里我要感谢SMTH AI版的alamarik和Graphics版的faintt) 导航栏: 研究群体 大拿主页 前沿期刊 GPL软件资源 搜索引擎 一、研究群体 http://www-2.cs.cmu.edu/~cil/vision.html 这是卡奈基梅隆大学的计算机视觉研究组的主页,上面提供很全的资料,从发表文章的下载到演示程序、测试图像、常用链接、相关软硬件,甚至还有一个搜索引擎。 http://www.cmis.csiro.au/IAP/zimage.htm 这是一个侧重图像分析的站点,一般。但是提供一个Image Analysis环境---ZIMAGE and SZIMAGE。 http://www.via.cornell.edu/ 康奈尔大学的计算机视觉和图像分析研究组,好像是电子和计算机工程系的。侧重医学方面的研究,但是在上面有相当不错资源,关键是它正在建设中,能够跟踪一些信息。 http://www2.parc.com/istl/groups/did/didoverview.shtml 有一个很有意思的项目:DID(文档图像解码)。 http://www-cs-students.stanford.edu/ 斯坦福大学计算机系主页,自己找吧:( http://www.fmrib.ox.ac.uk/analysis/ 主要研究:Brain Extraction Tool,Nonlinear noise reduction,Linear Image Registration, Automated Segmentation,Structural brain change analysis,motion correction,etc. http://www.cse.msu.edu/prip/ 这是密歇根州立大学计算机和电子工程系的模式识别--图像处理研究组,它的FTP上有许多的文章(NEW)。 http://pandora.inf.uni-jena.de/p/e/index.html 德国的一个数字图像处理研究小组,在其上面能找到一些不错的链接资源。 http://www-staff.it.uts.edu.au/~sean/CVCC.dir/home.html CVIP(used to be CVCC for Computer Vision and Cluster Computing) is a research group focusing on cluster-based computer vision within the Spiral Architecture. http://cfia.gmu.edu/ The mission of the Center for Image Analysis is to foster multi-disciplinary research in image, multimedia and related technologies by establishing links between academic institutes, industry and government agencies, and to transfer key technologies to help industry build next generation commercial and military imaging and multimedia systems. http://peipa.essex.ac.uk/info/groups.html 可以通过它来搜索全世界各地的知名的计算机视觉研究组(CV Groups),极力推荐。 二、图像处理GPL库 http://www.ph.tn.tudelft.nl/~klamer/cppima.html Cppima 是一个图像处理的C++函数库。这里有一个较全面介绍它的库函数的文档,当然你也可以下载压缩的GZIP包,里面包含TexInfo格式的文档。 http://iraf.noao.edu/ Welcome to the IRAF Homepage! IRAF is the Image Reduction and Analysis Facility, a general purpose software system for the reduction and analysis of astronomical data. http://entropy.brni-jhu.org/tnimage.html 一个非常不错的Unix系统的图像处理工具,看看它的截图。你可以在此基础上构建自己的专用图像处理工具包。 http://sourceforge.net/projects/ 这是GPL软件集散地,到这里找你想要得到的IP库吧。 三、搜索资源 当然这里基本的搜索引擎还是必须要依靠的,比如Google等,可以到我常用的链接看看。下面的链接可能会节省你一些时间: http://sal.kachinatech.com/ http://cheminfo.pku.edu.cn/mirrors/SAL/index.shtml 四、大拿网页 http://www.ai.mit.edu/people/wtf/ 这位可是MIT人工智能实验室的BILL FREEMAN。大名鼎鼎!专长是:理解--贝叶斯模型。 http://www.merl.com/people/brand/ MERL(Mitsubishi Electric Research Laboratory)中的擅长“Style Machine”高手。 http://research.microsoft.com/~ablake/ CV界极有声望的A.Blake 1977年毕业于剑桥大学三一学院并或数学与电子科学学士学位。之后在MIT,Edinburgh,Oxford先后组建过研究小组并成为Oxford的教授,直到1999年进入微软剑桥研究中心。主要工作领域是计算机视觉。 http://www-2.cs.cmu.edu/afs/cs.cmu.edu/user/har/Web/home.html 这位牛人好像正在学习汉语,并且搜集了诸如“两只老虎(Two Tigers)”的歌曲,嘿嘿:) 他的主页上面还有几个牛:Shumeet Baluja, Takeo Kanade。他们的Face Detection作的绝对是世界一流。他毕业于卡奈基梅隆大学的计算机科学系,兴趣是计算机视觉。 http://www.ifp.uiuc.edu/yrui_ifp_home/html/huang_frame.html 这位老牛在1963年就获得了MIT的博士学位!他领导的Image Lab比较出名的是指纹识别。 -------------------------------------------------------------------------------- 下面这些是我搜集的牛群(大部分是如日中天的Ph.D们),可以学习的是他们的Study Ways! Finn Lindgren(Sweden):Statistical image analysis http://www.maths.lth.se/matstat/staff/finn/ Pavel Paclik(Prague):statistical pattern recognition http://www.ph.tn.tudelft.nl/~pavel/ Dr. Mark Burge:machine learning and graph theory http://cs.armstrong.edu/burge/ yalin Wang:Document Image Analysis http://students.washington.edu/~ylwang/ Geir Storvik: Image analysis http://www.math.uio.no/~geirs/ Heidorn http://alexia.lis.uiuc.edu/~heidorn/ Joakim Lindblad:Digital Image Cytometry http://www.cb.uu.se/~joakim/index_eng.html S.Lavirotte: http://www-sop.inria.fr/cafe/Stephane.Lavirotte/ Sporring: scale-space techniques http://www.lab3d.odont.ku.dk/~sporring/ Mark Jenkinson:Reduction of MR Artefacts http://www.fmrib.ox.ac.uk/~mark/ Justin K. Romberg:digital signal processing http://www-dsp.rice.edu/~jrom/ Fauqueur:Image retrieval by regions of interest http://www-rocq.inria.fr/~fauqueur/ James J. Nolan:Computer Vision http://cs.gmu.edu/~jnolan/ Daniel X. Pape:Information http://www.bucho.org/~dpape/ Drew Pilant:remote sensing technology http://www.geo.mtu.edu/~anpilant/index.html 五、前沿期刊(TOP10) 这里的期刊大部分都可以通过上面的大拿们的主页间接找到,在这列出主要是为了节省直接想找期刊投稿的兄弟的时间:) IEEE Trans. On PAMI http://www.computer.org/tpami/index.htm IEEE Transactionson Image Processing http://www.ieee.org/organizations/pubs/transactions/tip.htm Pattern Recognition http://www.elsevier.com/locate/issn/00313203 Pattern Recognition Letters http://www.elsevier.com/locate/issn/01678655 神经网络 Neural Networks Tutorial Review http://hem.hj.se/~de96klda/NeuralNetworks.htm ftp://ftp.sas.com/pub/neural/FAQ.html Image Compression with Neural Networks http://www.comp.glam.ac.uk/digimaging/neural.htm Backpropagator's Review http://www.dontveter.com/bpr/bpr.html Bibliographies on Neural Networks http://liinwww.ira.uka.de/bibliography/Neural/ Intelligent Motion Control with an Artificial Cerebellum http://www.q12.org/phd.html Kernel Machines http://www.kernel-machines.org/ Some Neural Networks Research Organizations http://www.ieee.org/nnc/ http://www.inns.org/ Neural Network Modeling in Vision Research http://www.rybak-et-al.net/nisms.html Neural Networks and Machine Learning http://learning.cs.toronto.edu/ Neural Application Software http://attrasoft.com Neural Network Toolbox for MATLAB http://www.mathworks.com/products/neuralnet/ Netlab Software http://www.ncrg.aston.ac.uk/netlab/ Kunama Systems Limited http://www.kunama.co.uk/ Computer Vision Computer Vision Homepage, Carnegie Mellon University www.cs.cmu.edu/~cil/vision.html Annotated Computer Vision Bibliography http://iris.usc.edu/Vision-Notes/bibliography/contents.html http://iris.usc.edu/Vision-Notes/rosenfeld/contents.html Lawrence Berkeley National Lab Computer Vision and Robotics Applications http://www-itg.lbl.gov/ITG.hm.pg.docs/VISIon/vision.html CVonline by University of Edinburgh The Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision, www.dai.ed.ac.uk/CVonline Computer Vision Handbook, www.cs.hmc.edu/~fleck/computer-vision-handbook Vision Systems Courseware www.cs.cf.ac.uk/Dave/Vision_lecture/Vision_lecture_caller.html Research Activities in Computer Vision http://www-syntim.inria.fr/syntim/analyse/index-eng.html Vision Systems Acronyms www.vision-systems-design.com/vsd/archive/acronyms.html Dictionary of Terms in Human and Animal Vision http://cns-web.bu.edu/pub/laliden/WWW/Visionary/Visionary.html Metrology based on Computer Vision www.cranfield.ac.uk/sme/amac/research/metrology/metrology.html Digital Photography Digital Photography, Scanning, and Image Processing www.dbusch.com/scanners/scanners.html Educational Resources, Universities Center for Image Processing in Education www.cipe.com Library of Congress Call Numbers Related to Imaging Science by Rochester Institute of Technology http://wally2.rit.edu/pubs/guides/imagingcall.html Mathematical Experiences through Image Processing, University of Washington www.cs.washington.edu/research/metip/metip.html Vismod Tech Reports and Publications, MIT http://vismod.www.media.mit.edu/cgi-bin/tr_pagemaker Vision Lab PhD dissertation list, University of Antwerp http://wcc.ruca.ua.ac.be/~visielab/theses.html INRIA (France) Research Projects: Human-Computer Interaction, Image Processing, Data Management, Knowledge Systems www.inria.fr/Themes/Theme3-eng.html Image Processing Resources http://eleceng.ukc.ac.uk/~rls3/Contents.htm Publications of Carsten Steger http://www9.informatik.tu-muenchen.de/people/steger/publications.html FAQs comp.dsp FAQ www.bdti.com/faq/dsp_faq.htm Robotics FAQ www.frc.ri.cmu.edu/robotics-faq Where's the sci.image.processing FAQ? www.cc.iastate.edu/olc_answers/packages/graphics/sci.image.processing.faq.html comp.graphics.algorithms FAQ, Section 3, 2D Image/Pixel Computations www.exaflop.org/docs/cgafaq Astronomical Image Processing System FAQ www.cv.nrao.edu/aips/aips_faq. html 更多见 http://blog.sina.com.cn/charming0577
Image Processing Contrast Enhancement and Filtering ADAPT_HIST_EQUAL- Performs adaptive histogram equalization BUTTERWORTH- Returns the absolute value of the low-pass Butterworth kernel. BYTSCL- Scales all values of an array into range of bytes. CANNY- Implements the Canny edge-detection algorithm. CONVOL- Convolves two vectors or arrays. DIGITAL_FILTER- Calculates coefficients of a non-recursive, digital filter. FFT- Returns the Fast Fourier Transform of an array. HILBERT- Constructs a Hilbert transform. HIST_EQUAL- Histogram-equalizes an image. IR_FILTER - Performs the infinite or finite impulse response filter on data. LEEFILT- Performs the Lee filter algorithm on an image array. MEDIAN- Returns the median value of Array or applies a median filter. ROBERTS- Returns an approximation of Roberts edge enhancement. SMOOTH- Smooths with a boxcar average. SOBEL- Returns an approximation of Sobel edge enhancement. UNSHARP_MASK - Performs an unsharp-mask sharpening filter on a two-dimensional array or a truecolor image. See Also- Wavelet Toolkit Feature Extraction/Image Segmentation CONTOUR- Draws a contour plot. DEFROI- Defines an irregular region of interest of an image. HISTOGRAM- Computes the density function of an array. HOUGH- Returns the Hough transform of a two-dimensional image. IMAGE_STATISTICS- Computes sample statistics for a given array of values. ISOCONTOUR- Interprets the contouring algorithm found in the IDLgrContour object. ISOSURFACE- Returns topologically consistent triangles by using oriented tetrahedral decomposition. LABEL_REGION- Labels regions (blobs) of a bi-level image. MAX- Returns the value of the largest element of Array. MEDIAN- Returns the median value of Array or applies a median filter. MIN- Returns the value of the smallest element of an array. PROFILES- Interactively examines image profiles. RADON- Returns the Radon transform of a two-dimensional image. REGION_GROW- Perform region growing. SEARCH2D- Finds objects or regions of similar data within a 2D array. THIN- Returns the skeleton of a bi-level image. UNIQ- Returns subscripts of the unique elements in an array. WATERSHED- Applies the morphological watershed operator to a grayscale image. WHERE- Returns subscripts of nonzero array elements. Image Display DISSOLVE- Provides a digital dissolve effect for images. IDLgrImage- Creates an image object that represents a mapping from a 2D array of data values to a 2D array of pixel colors. IDLgrPalette- Represents a color lookup table that maps indices to red, green, and blue values. IIMAGE- Creates an iTool and associated user interface (UI) configured to display and manipulate image data. RDPIX- Interactively displays image pixel values. SLIDE_IMAGE- Creates a scrolling graphics window for examining large images. TV- Displays an image. To scale and display the image, use TVSCL. TVCRS- Manipulates the image display cursor. TVLCT- Loads display color tables. TVSCL- Scales and displays an image. XOBJVIEW- Displays object viewer widget. XOBJVIEW_ROTATE- Programmatically rotate the object currently displayed in XOBJVIEW. XOBJVIEW_WRITE_IMAGE- Write the object currently displayed in XOBJVIEW to an image file. ZOOM- Zooms portions of the display. ZOOM_24- Zooms portions of true-color (24-bit) display. Image Geometry Transformations CONGRID- Resamples an image to any dimensions. EXPAND- Shrinks/expands image using bilinear interpolation. EXTRAC- Returns sub-matrix of input array. Array operators (e.g., * and :) should usually be used instead. INTERPOLATE- Returns an array of interpolates. INVERT- Computes the inverse of a square array. POLY_2D- Performs polynomial warping of images. POLYWARP- Performs polynomial spatial warping. REBIN- Resizes a vector or array by integer multiples. REFORM- Changes array dimensions without changing the total number of elements. REVERSE- Reverses the order of one dimension of an array. ROT- Rotates an image by any amount. ROTATE- Rotates/transposes an array in multiples of 90 degrees. SHIFT- Shifts elements of vectors or arrays by a specified number of elements. TRANSPOSE- Transposes an array. WARP_TRI- Warps an image using control points. Morphological Image Operators DILATE- Implements morphologic dilation operator on binary and grayscale images. ERODE- Implements the erosion operator on binary and grayscale images and vectors. LABEL_REGION- Labels regions (blobs) of a bi-level image. MORPH_CLOSE- Applies closing operator to binary or grayscale image. MORPH_DISTANCE- Estimates N-dimensional distance maps, which contain for each foreground pixel the distance to the nearest background pixel, using a given norm. MORPH_GRADIENT- Applies the morphological gradient operator to a grayscale image. MORPH_HITORMISS- Applies the hit-or-miss operator to a binary image. MORPH_OPEN- Applies the opening operator to a binary or grayscale image. MORPH_THIN- Performs a thinning operation on binary images. MORPH_TOPHAT- Applies top-hat operator to a grayscale image. WATERSHED- Applies the morphological watershed operator to a grayscale image. Regions of Interest CW_DEFROI- Creates compound widget used to define region of interest. DEFROI- Defines an irregular region of interest of an image. DRAW_ROI- Draws region or group of regions to current Direct Graphics device. IDLanROI- Represents a region of interest used for analysis. IDLanROIGroup- Analytical representation of a group of regions of interest. IDLgrROI- Object graphics representation of a region of interest. IDLgrROIGroup- Object Graphics representation of a group of regions of interest. LABEL_REGION- Labels regions (blobs) of a bi-level image. REGION_GROW- Grows an initial region to include all areas that match specified constraints. XROI- Utility for defining regions of interest, and obtaining geometry and statistical data about these ROIs.
感谢水木上同领域的同学分享,有了他的整理,让我很方便的获得了CV方面相关的经典论文,我也顺便整理一下,把pdf中的文字贴到网页上,方便其它人更直观的获取所要内容~~~ 资料的下载链接为: http://iask.sina.com.cn/u/2252291285/ish?folderid=775855 以下为该同学的整理的综述: “ 前言:最近由于工作的关系,接触到了很多篇以前都没有听说过的经典文章,在感叹这些文章伟大的同时,也顿感自己视野的狭小。 想在网上找找计算机视觉界的经典文章汇总,一直没有找到。失望之余,我决定自己总结一篇,希望对 CV 领域的童鞋们有所帮助。由于自己的视野比较狭窄,肯定也有很多疏漏,权当抛砖引玉了,如果你觉得哪篇文章是非常经典的,也可以把相关信息连带你的昵称发给我,我好补上。我的信箱 xdyang.ustc@gmail.com 文章主要来源:PAMI, IJCV, TIP, CVIU, PR, IVC, CVGIU, CVPR, ICCV, ECCV, NIPS, SIGGRAPH, BMVC等 主要参考网站: Google scholar, citeseer, cvpapers, opencv 中英文官方网站 主要参考书籍: 数字图像处理 第三版 冈萨雷斯等 图像处理,分析和机器视觉 第三版 Sonka等(非常非常好的一本书) 学习OpenCV 计算机视觉:算法与应用 文章按时间排序,排名不分先后,^_^。每一行最后一栏是我自己加的注释,如果不喜欢可以无视之,如果有不对的地方还请告诉我,免得继续出丑。 给出的文章有些是从google scholar或者citeseer上拷贝下来的,所以有链接。所有的文章在网上都很容易找到。有空的时候我会把它们全部整理出来,逐步上传到ishare.iask.sina.com 由于整理的很仓促,时间也很短,还有很多不完善的地方。我会不断改进,并不时上传新版本。 上传地址为 http://iask.sina.com.cn/u/2252291285/ish?folderid=775855 最后更新:2012/3/14 1990 年之前 Peter Burt,EdwardAdelson The Laplacian Pyramid as A Compact Image Code 虽说这个Laplacian Pyramid是有冗 余的,但使用起来非常简单方便, 对理解小波变换也非常有帮助。这 位Adelson是W.T.Freeman的老板, 都是大牛. J Canny A Computational Approach to Edge Detection 经典不需要解释。在 Sonka的书里 面对这个算法也有比较详细的描 述。 S Mallat. A theory for multiresolution signal decomposition: The wavelet representation Mallat的代表作 M Kass, AWitkin, D Terzopoulos. Snakes: active contour models Deformable model的开山鼻祖。 RMHARALICK Textural Features for ImageClassification 这三篇都是关于纹理特征的,虽然过去这么多年了,现在在检索和识别中依然很有用。 RMHARALICK Statistical and structural approaches Tamura等 Texture features corresponding tovisual perception A PDempster, NM Laird, D BRubin. 1977 Maximum likelihood from incompletedata via the EM algorithm EM 算法在计算机视觉中有着非常重要的作用 L Rabiner.1989 A Tutorial on Hidden Markov Modelsand Selected Applications in SpeechRecognition HMM 同样是计算机视觉必须掌握的一项工具 B D Lucas, TKanade An iterative image registrationtechnique with an application to stereo- vision Lucas 光流法 J R Quinlan Induction of decision trees 偏模式识别和机器学习一点 1990 年 P Perona, JMalik.PAMI Scale-space and edge detectionusing anisotropic diffusion 关于 scale space 最早的一篇论文之一,引用率很高 T Lindeberg Scale-space for discrete signals. Lindeberg 关于 scale space 比较早的一篇,后续还有好几篇 anzad, A.;Hong, Y.H. Invariant image recognition byZernike moments Zernike moment,做过模式识别或者检索的应该都知道这个东东 1991 年 W Freeman, EAdelson. The design and use of steerablefilters Freeman最早的一篇力作,也是我读的第一篇学术论文。现在Freeman在 MIT 风生水起,早已是IEEE Fellow了 Michael J.Swain , DanaH. Ballard Color Indexing. google scholar 上引用将近五千次 MA TurkCVPR Face recognition using eigenfaces 1992 年 L G Brown. A survey of image registrationtechniques. 比较早的一篇关于配准的综述了 1993 年 S G Mallat, ZZhang. Matching pursuits withtime-frequency dictionaries Mallat另一篇关于小波的文章,不研究小波的可以无视之 L Vincent. Morphological grayscalereconstruction in image analysis:Applications and efficient algorithms DPHuttenlocher Comparing images using theHausdorff distance Google scolar 上引用2200多次 1994 年 J Shi, C Tomasi. Good feature to track. Tomasi这个名字还会出现好几次,真的很牛 Linderberg Scale-space theory in computervision J L Barron, DJ Fleet, S S Beauchemin. Performance of optical flowtechniques. 1995 年 R Malladi, JSethian, BVemuri. Shape Modeling with FrontPropagation: A Level Set Approach Level set的经典文章 TF COOTES Active Shape Models-Their Trainingand Application ASM MA Stricker Similarity of color images 颜色检索相关 C Cortes, VVapnik. Support-vector networks. SVM 在计算机视觉中也有着非常重要的地位 1996 年 T MCINERNEY. Deformable models in medicalimage analysis: A survey 活动模型的一篇较早的综述 Tai Sing Lee Image Representation Using 2DGabor Wavelets Google引用也有近千次 Amir Said, A.Pearlman A New, Fast, and Efficient ImageCodec Based on Set Partitioning inHierarchical Tree SPIHT。图像压缩领域与 EBCOT齐名的经典算法。 L P Kaelbling, ML Littman, A WMoore. Reinforcement learning: A survey 机器学习里面的一篇综述,引用率比较高,就列在这了。 B. S.Manjunath and W.Y. Ma Texture features for browsing andretrieval of image data 检索的文章比较多,其实它们的应用不仅仅是检索。只要是需要提取特征的地方,检索里面的方法都可以用到 comparing images using colorcoherence vectors 检索中的CCV方法 Image retrieval using color andshape 关于形状特征后面有一篇综述 1997 年 V Caselles, RKimmel, GSapiro. Geodesic active contours 活动轮廓模型的一个小分支 R E Schapire, YFreund, PBartlett, W SLee. Boosting the Margin: A NewExplanation for the Effectiveness ofVoting Methods. Schapire 和 Freund 发 明 了Adaboost,给计算机视觉带来了不少经典算法 F Maes, DVandermeulen,G Marchal, PSuetens. Multimodality image registration bymaximization of mutual information 互信息量配准 E Osuna, RFreund, FGirosi. Training support vector machines: Anapplication to face detection. SVM在人脸检测中的应用。不过人脸检测最经典的方法应 该是Viola-Jones J Huang, SKumar, MMitra, W-J Zhu,R Zabih. Image indexing using colorcorrelogram Color correlogram,检索中的又一个颜色特征。和前面的 CCV 以及颜色矩特征基本上覆盖了所有的颜色特征。 Y Freund, RSchapire. A decisiontheoretic generalization ofon-line learning and an application toboosting. Adaboost的经典文章 1998 年 1998 年是图像处理和计算机视觉经典文章井喷的一年。大概从这一年开始,开始有了新的趋势。由于竞争的加剧,一些好的算法都先发在会议上了,先占个坑,等过一两年之后再扩展到会议上。 T Lindeberg Feature detection with automaticscale selection Linderberg的 scale space到此为止基本结束了。在一些边缘提取,道路或者血管检测中,scale space 确实是一种很不错的工具 C J C Burges. A tutorial on support vector machinesfor pattern recognition. 使用 svm的话,这篇文章应该是必读的了。比 95 年那篇原始文章引用率还高 M Isard, ABlake. CONDENSATION – Conditional TrackingDensity Propagation for Visual Tracking中的经典文章了 L Page, S Brin,R Motwani, T Winograd The PageRank citation ranking:bringing order to the web 这篇文章应该不属于 CV 的范畴,鉴于作者的大名鼎鼎,暂且列在这 C Tomasi, RManduchi. Bilateral filtering for gray and colorimages. 做过图像滤波平滑去噪或者 HDR的应该都知道Bilateral filter。原理非常非常简单,简单到一个公式就可以概括这篇文章,简单到实在无法扩充到期刊。这也是 Tomasi 第二次出现了。一直很纳闷,这个很直观的思想在这之前怎么就从来没人提呢。 C Xu, J LPrince. Snakes, shapes and gradient vectorflow. 终于碰到中国人写的文章了,很荣幸还是校友。GVF是 snake和levelset领域的重要分支和方法 Wim Sweldens. The lifting scheme: A construction ofsecond generation wavelets. 第二代小波。真正让小波有了实用价值,在 JPEG2000 中就采用的提升小波。个人更喜欢的是下一篇,简单易懂,字体也大 DaubechiesWim Sweldens Factoring wavelet transforms intolifting steps 另一位作者也很牛,小波十讲的作者 H A Rowley, SBaluja, TKanade. Neural Network-based FaceDetection. 做人脸的应该是必看的了。不做人脸的话应该可以不用看吧 J B A Maintz,M A Viergever. A survey of medical imageregistration. 关于图像配准的另一篇综述 T F Cootes, GJ Edwards, CJ Taylor. Active Appearance Models AAM 1999 年 D Lowe. Object Recognition from LocalScale-invariant Features 大名鼎鼎的SIFT,后面有一篇IJCV上的 Journal版本,更全面一点。 R E Schapire. A brief Introduction to Boosting 还是 boosting D M Gavrila. The visual analysis of humanmovements: a survey 综述文章的引用一般都比较高 Y Rui, T SHuang, S FChange. Image retrieval: current techniques,promising directions, and openissues TSHuang小组对检索的一个总结 J K Aggarwal, QCai. Human motion analysis: a review 人体运动分析的一个综述 2000 年 世纪之交,各种综述都出来了 J Shi, J Malik. Normalized Cuts and ImageSegmentation NCuts的引用率相当高,Jianbo Shi也因为这篇文章成为计算机视觉界引用率最高的作者之一 Z Zhang. A Flexible New Technique forCamera Calibration 张正友的关于摄像机标定的经典短文 A K Jain, R P WDuin, J C Mao. Statistical pattern recognition: areview. 统计模式识别综述,这一年 pami上两篇很有名的综述之一。 在这里推荐 Web 写的 Statistical PatternRecognition第三版,相当不错,网上有电子版。 C Stauffe Learning Patterns of Activity UsingReal-Time Tracking 搜 TLD 的时候发现这篇文章引用率也很高,两千多次。还没来得及读。 D Taubman. High performance Scalable ImageCompression With EBCOT EBCOT,JPEG2000 中的算法 A W MSmeulders, MWorring, SSantini, AGupta, R Jain. Content-based image retrieval at theend of the early years 在世纪之交对图像检索的一篇很权威的综述。感觉在这之后检索的研究也没那么热了。不过在工业界热度依旧,各大网上购物平台,比如淘宝, 亚马逊,京东等都在做这方面的研发,衣服检索是一个很不错的应用点。 M Pantic, L J MRothkrantz. Automatic analysis of facialexpressions: the state of the art. N Paragios, RDeriche. Geodesic active contours and levelsets for the detection and tracking ofmoving objects 使用 level set做跟踪 Y Rubner, CTomasi, LGuibas. TThe earth mover’s distance as ametric for image retrieval. EMD算法。Tomasi再次出现 PicToSeek Combining Color andShape Invariant Features for ImageRetrieval 依然是检索特征 2001 年 Paul Viola,Michael JJones. Robust real-time object detection 这是一篇很牛的文章,在人脸检测上几乎成了标准。比较坑爹的是,号称发在IJCV2001 上,但怎么找也找不到。应该是 IJCV2004年的那篇“Robust real-time face detection”吧。他们在这一年另一篇比较出名的文章是在CVPR上的“Rapid ObjectDetection using a Boosted Cascadeof Simple Features”这篇才是04年那篇著名文章的会议版。 Y Boykov,Kolmogorov. An experimental comparison ofmin-cut/max-flow algorithms forenergy minimization in vision. 俄罗斯人在 graph cut 领域开始发力了 T Moeslund, EGranum. A Survey of Computer Vision BasedHuman Motion Capture 人体运动综述 T F Chan, LVese. Active contours without edges. Snake 和 level set领域的经典文章 A M Martinez,A C Kak. PCA versus LDA PCA 也是计算机视觉中非掌握不可的工具。LDA在模式识别中有很重要的地位 BS Manjunath Color and texture descriptors 颜色和纹理的描述子,在识别中很有用 2002 年 D Comaniciu, PMeer. Mean shift: A robust approachtoward feature space analysis. Mean shift的经典文章。前两天发现 Comaniciu 已经是 IEEE Fellow了 Ming-HusanYang, David JKriegman,NarendraAhuja. Detecting Faces in Images: ASurvey. 人脸检测综述,引用率想不高都难 R Hsu, MAbdel-Mottaleb. Face Detection in Color Images. 依然是人脸检测,名字都起得这么霸气 J-L Starck, E JCandès, D LDonoho. The curvelet transform for imagedenoising. Geometrical wavelet 中的一篇代表 作 。 其 他 的 如 ridgelet,contourlet, bandelet 等在这里就不赘述了。研究这方面的很容易找到这方面的经典文献。个人以为不研究这方面的看了后对自己的研究也不会有多大启发。曾经以为这个方向会很火,到最后还是没火起来。 我觉得原因可能是现在存储和传输能力的大大提高,使得对压缩的需求没有那么大了,这方面的研究自然就停滞了,就如同JPEG2000没有成气候 Shape matching and objectrecognition using shape contexts Shape context。用形状匹配达到目标识别目的。这方面最经典的文章了。随后后续也有一些这方面的文章,但基本都是很小的改进或者应用。作者提供了原码,可以在 matlab上运行看看效果。 N Paragios, RDeriche. Geodesic active regions and levelset methods for supervised texturesegmentation Statistical Color Models withApplication to Skin Detection A tutorial on particle filters for onlinenonlinear non-Gaussian Bayesiantracking particle filter 的一个综述 2003 年 W Zhao, RChellappa, PJ Phillips, ARosenfeld. Face recognition: A literature survey. 人脸检测的综述 J Sivic, AZisserman. Video Google: A text retrievalapproach to object matching invideos. 好像是Visual words的起源文章。引用率很高,先列出来再看。 D Comaniciu,V Ramesch,P Meer. Kernel-Based Object Tracking. 基于核的跟踪。 B Zitová, JFlusser. Image registration methods: Asurvey. 又一篇图像配准的综述。做图像配准的比较有福气,综述很多 KMikolajczyk,C Schmid. A performance evaluation of localdescriptors. 比较各种描述子的,包括SIFT M JWainwright,M I Jordan. Graphical models, exponentialfamilies, and variational inference. 乔丹的名气太大,不露露脸说不过去 J Portilla, VStrela, MWainwright, ESimoncelli. Image denoising using scalemixtures of gaussians in the waveletdomain. 图像去噪,小波变换,混合高斯 Robert E.Schapire The Boosting Approach to MachineLearning An Overview boosting作者自己写的综述,自然值得一看。 2004 年 Lucas-Kanade 20 Years On AUnifying Framework 引用文章摘要的第一句话Since the Lucas-Kanade algorithmwas proposed in 1981 imagealignment has become one of themostwidely used techniques in computervision. Applications range fromoptical flow and tracking to layeredmotion, mosaic construction, andface coding. D G Lowe. Distinctive image features fromscale-invariant keypoints. SIFT,不解释 Chih-ChungChang,Chih-Jen Lin. LIBSVM: A library for support vectormachines 我实在怀疑引用这篇文章的人是否都看过这篇文章。貌似不看这篇文章也可以使用 LIBSVM Z Wang, A CBovik, H RSheikh, E PSimoncelli. Image quality assessment: Fromerror visibility to structural similarity 图像质量评价,最近 Bovik 还有一篇类似的文章也刊登在 TIP上 Y Ke, RSukthankar. Pca-sift: a more distinctiverepresentation for local imagedescriptors SIFT 的变形 Review of shape representation anddescription techniques Efficient Graph-Based ImageSegmentation 2005 年 N Dalal, BTriggs. Histograms of oriented gradients forhuman detection. HOG 虽然很新,但很经典 A C Berg, T LBerg, J Malik. Shape matching and objectrecognition using low distortioncorrespondences. 还是 shape matching S Roth, MBlack. Fields of experts: A framework forlearning image priors. 这篇应该要归结到图像统计特性的范畴吧 Z Tu, X Chen,A L Yuille, S CZhu. Image parsing: Unifyingsegmentation, detection, andrecognition. Geodesic active regions and level setmethods for motion estimation andtracking Chunming Li,ChenyangXu,ChangfengGui, and Martin D. Fox Level Set Evolution WithoutRe-initialization: A New VariationalFormulation 这篇文章解决了level set中需要不停的重初始化的问题。在 2010 年的 TIP上有一篇 Journal版本Distance Regularized Level SetEvolution and its Application toImage Segmentation A Performance Evaluation of LocalDescriptors 前面那篇是会议的,这篇是 PAMI上的。比较各种描述子的,包括SIFT 2006 年 D Donoho. Compressed sensing. CS 压缩感知 最近很火的一个名词 Greg Welch,Gary Bishop. An introduction to the Kalman Filter. kalman滤波 S Lazebnik, CSchmid, JPonce. Beyond bags of features: spatialpyramid matching for recognizingnatural scene categories. Visual words Xiaojin Zhu. Semi-supervised learning literaturesurvey. A Yilmaz, OJaved, MShah. Object Tracking: A survey. tracking的一篇综述 Image Alignment and Stitching: ATutorial 2007 年 A Review of Statistical Approaches toLevel Set Segmentation: IntegratingColor, Texture, Motion and Shape The Appearance of Human Skin:A Survey Local Invariant Feature Detectors: ASurvey 2008 年 H Bay, A Ess,T Tuytelaars,L V Gool. SURF: Speeded Up Robust Features. K E A van deSande, TGevers, C GM Snoek. Evaluation of Color Descriptors forObject and Scene Recognition M Yang A Survey of Shape FeatureExtraction Techniques 虽然这篇文章的引用率目前来看并不高,但个人认为这是一篇在shape feature方面很不错的文章 P.Felzenszwalb,D. McAllester,D. Ramanan A Discriminatively Trained,Multiscale, Deformable Part Model 2008 年的 CVPR,到现在引用已有四百多次,潜力巨大。rosepink提供 2009 年 J Wright, A YYang, AGanesh, S SSastry, Ma. Robust Face Recognition via SparseRepresentation. B Settles. Active learning literature survey 2010 年 2011 年 Hough Forests for Object Detection,Tracking, and Action Recognition Robust Principal ComponentAnalysis? Candes 和 UIUC 的Ma Yi等人 2012 年 Zdenek Kalal,KrystianMikolajczyk,and Jiri Matas, Tracking-Learning-Detection PAMI上的,虽然还没有正式发表,但肯定会火。在作者的主页上有几篇相关的会议文章, demo和code。用到了 Lucas-Kanade方法 (完)“
作图像处理方面的研究工作,最重要的两个问题:其一是要把握住国际上最前沿的内容;其二是所作工作要具备很高的实用背景。解决第一个问题的办法就是找出这个方向公认最牛的几个超级大拿(看看他们都在作什么)和最权威的出版物(阅读上面最新的文献),解决第二个问题的办法是你最好能够找到一个实际应用的项目,边做边写文章。 做好这几点的途径之一就是充分利用网络资源,特别是权威网站和大拿们的个人主页。下面是我收集的一些资源,希望对大家有用. 研究群体 大拿主页 前沿期刊 GPL软件资源 搜索引擎 一、研究群体 http://www-2.cs.cmu.edu/~cil/vision.html 这是卡奈基梅隆大学的计算机视觉研究组的主页,上面提供很全的资料,从发表文章的下载到演示程序、测试图像、常用链接、相关软硬件,甚至还有一个搜索引擎。 http://www.cmis.csiro.au/IAP/zimage.htm 这是一个侧重图像分析的站点,一般。但是提供一个Image Analysis环境---ZIMAGE and SZIMAGE。 http://www.via.cornell.edu/ 康奈尔大学的计算机视觉和图像分析研究组,好像是电子和计算机工程系的。侧重医学方面的研究,但是在上面有相当不错资源,关键是它正在建设中,能够跟踪一些信息。 http://www2.parc.com/istl/groups/did/didoverview.shtml 有一个很有意思的项目:DID(文档图像解码)。 http://www-cs-students.stanford.edu/ 斯坦福大学计算机系主页,自己找吧:( http://www.fmrib.ox.ac.uk/analysis/ 主要研究:Brain Extraction Tool,Nonlinear noise reduction,Linear Image Registration, Automated Segmentation,Structural brain change analysis,motion correction,etc. http://www.cse.msu.edu/prip/ 这是密歇根州立大学计算机和电子工程系的模式识别--图像处理研究组,它的FTP上有许多的文章(NEW)。 http://pandora.inf.uni-jena.de/p/e/index.html 德国的一个数字图像处理研究小组,在其上面能找到一些不错的链接资源。 http://www-staff.it.uts.edu.au/~sean/CVCC.dir/home.html CVIP(used to be CVCC for Computer Vision and Cluster Computing) is a research group focusing on cluster-based computer vision within the Spiral Architecture. http://cfia.gmu.edu/ The mission of the Center for Image Analysis is to foster multi-disciplinary research in image, multimedia and related technologies by establishing links between academic institutes, industry and government agencies, and to transfer key technologies to help industry build next generation commercial and military imaging and multimedia systems. http://peipa.essex.ac.uk/info/groups.html 可以通过它来搜索全世界各地的知名的计算机视觉研究组(CV Groups),极力推荐。 二、图像处理GPL库 http://www.ph.tn.tudelft.nl/~klamer/cppima.html Cppima 是一个图像处理的C++函数库。这里有一个较全面介绍它的库函数的文档,当然你也可以下载压缩的GZIP包,里面包含TexInfo格式的文档。 http://iraf.noao.edu/ Welcome to the IRAF Homepage! IRAF is the Image Reduction and Analysis Facility, a general purpose software system for the reduction and analysis of astronomical data. http://entropy.brni-jhu.org/tnimage.html 一个非常不错的Unix系统的图像处理工具,看看它的截图。你可以在此基础上构建自己的专用图像处理工具包。 http://sourceforge.net/projects/ 这是GPL软件集散地,到这里找你想要得到的IP库吧。 三、搜索资源 当然这里基本的搜索引擎还是必须要依靠的,比如Google等,可以到我常用的链接看看。下面的链接可能会节省你一些时间: http://sal.kachinatech.com/ http://cheminfo.pku.edu.cn/mirrors/SAL/index.shtml 四、大拿网页 http://www.ai.mit.edu/people/wtf/ 这位可是MIT人工智能实验室的BILL FREEMAN。大名鼎鼎!专长是:理解--贝叶斯模型。 http://www.merl.com/people/brand/ MERL(Mitsubishi Electric Research Laboratory)中的擅长“Style Machine”高手。 http://research.microsoft.com/~ablake/ CV界极有声望的A.Blake 1977年毕业于剑桥大学三一学院并或数学与电子科学学士学位。之后在MIT,Edinburgh,Oxford先后组建过研究小组并成为Oxford的教授,直到1999年进入微软剑桥研究中心。主要工作领域是计算机视觉。 http://www-2.cs.cmu.edu/afs/cs.cmu.edu/user/har/Web/home.html 这位牛人好像正在学习汉语,并且搜集了诸如“两只老虎(Two Tigers)”的歌曲,嘿嘿:) 他的主页上面还有几个牛:Shumeet Baluja, Takeo Kanade。他们的Face Detection作的绝对是世界一流。他毕业于卡奈基梅隆大学的计算机科学系,兴趣是计算机视觉。 http://www.ifp.uiuc.edu/yrui_ifp_home/html/huang_frame.html 这位老牛在1963年就获得了MIT的博士学位!他领导的Image Lab比较出名的是指纹识别。 -------------------------------------------------------------------------------- 下面这些是我搜集的牛群(大部分是如日中天的Ph.D们),可以学习的是他们的Study Ways! Finn Lindgren(Sweden):Statistical image analysis http://www.maths.lth.se/matstat/staff/finn/ Pavel Paclik(Prague):statistical pattern recognition http://www.ph.tn.tudelft.nl/~pavel/ Dr. Mark Burge:machine learning and graph theory http://cs.armstrong.edu/burge/ yalin Wang:Document Image Analysis http://students.washington.edu/~ylwang/ Geir Storvik: Image analysis http://www.math.uio.no/~geirs/ Heidorn http://alexia.lis.uiuc.edu/~heidorn/ Joakim Lindblad:Digital Image Cytometry http://www.cb.uu.se/~joakim/index_eng.html S.Lavirotte: http://www-sop.inria.fr/cafe/Stephane.Lavirotte/ Sporring: scale-space techniques http://www.lab3d.odont.ku.dk/~sporring/ Mark Jenkinson:Reduction of MR Artefacts http://www.fmrib.ox.ac.uk/~mark/ Justin K. Romberg:digital signal processing http://www-dsp.rice.edu/~jrom/ Fauqueur:Image retrieval by regions of interest http://www-rocq.inria.fr/~fauqueur/ James J. Nolan:Computer Vision http://cs.gmu.edu/~jnolan/ Daniel X. Pape:Information http://www.bucho.org/~dpape/ Drew Pilant:remote sensing technology http://www.geo.mtu.edu/~anpilant/index.html 五、前沿期刊(TOP10) 这里的期刊大部分都可以通过上面的大拿们的主页间接找到,在这列出主要是为了节省直接想找期刊投稿的兄弟的时间:) IEEE Trans. On PAMI http://www.computer.org/tpami/index.htm IEEE Transactionson Image Processing http://www.ieee.org/organizations/pubs/transactions/tip.htm Pattern Recognition http://www.elsevier.com/locate/issn/00313203 Pattern Recognition Letters http://www.elsevier.com/locate/issn/01678655 神经网络 Neural Networks Tutorial Review http://hem.hj.se/~de96klda/NeuralNetworks.htm ftp://ftp.sas.com/pub/neural/FAQ.html Image Compression with Neural Networks http://www.comp.glam.ac.uk/digimaging/neural.htm Backpropagator's Review http://www.dontveter.com/bpr/bpr.html Bibliographies on Neural Networks http://liinwww.ira.uka.de/bibliography/Neural/ Intelligent Motion Control with an Artificial Cerebellum http://www.q12.org/phd.html Kernel Machines http://www.kernel-machines.org/ Some Neural Networks Research Organizations http://www.ieee.org/nnc/ http://www.inns.org/ Neural Network Modeling in Vision Research http://www.rybak-et-al.net/nisms.html Neural Networks and Machine Learning http://learning.cs.toronto.edu/ Neural Application Software http://attrasoft.com Neural Network Toolbox for MATLAB http://www.mathworks.com/products/neuralnet/ Netlab Software http://www.ncrg.aston.ac.uk/netlab/ Kunama Systems Limited http://www.kunama.co.uk/ Computer Vision Computer Vision Homepage, Carnegie Mellon University www.cs.cmu.edu/~cil/vision.html Annotated Computer Vision Bibliography http://iris.usc.edu/Vision-Notes/bibliography/contents.html http://iris.usc.edu/Vision-Notes/rosenfeld/contents.html Lawrence Berkeley National Lab Computer Vision and Robotics Applications http://www-itg.lbl.gov/ITG.hm.pg.docs/VISIon/vision.html CVonline by University of Edinburgh The Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision, www.dai.ed.ac.uk/CVonline Computer Vision Handbook, www.cs.hmc.edu/~fleck/computer-vision-handbook Vision Systems Courseware www.cs.cf.ac.uk/Dave/Vision_lecture/Vision_lecture_caller.html Research Activities in Computer Vision http://www-syntim.inria.fr/syntim/analyse/index-eng.html Vision Systems Acronyms www.vision-systems-design.com/vsd/archive/acronyms.html Dictionary of Terms in Human and Animal Vision http://cns-web.bu.edu/pub/laliden/WWW/Visionary/Visionary.html Metrology based on Computer Vision www.cranfield.ac.uk/sme/amac/research/metrology/metrology.html Digital Photography Digital Photography, Scanning, and Image Processing www.dbusch.com/scanners/scanners.html Educational Resources, Universities Center for Image Processing in Education www.cipe.com Library of Congress Call Numbers Related to Imaging Science by Rochester Institute of Technology http://wally2.rit.edu/pubs/guides/imagingcall.html Mathematical Experiences through Image Processing, University of Washington www.cs.washington.edu/research/metip/metip.html Vismod Tech Reports and Publications, MIT http://vismod.www.media.mit.edu/cgi-bin/tr_pagemaker Vision Lab PhD dissertation list, University of Antwerp http://wcc.ruca.ua.ac.be/~visielab/theses.html INRIA (France) Research Projects: Human-Computer Interaction, Image Processing, Data Management, Knowledge Systems www.inria.fr/Themes/Theme3-eng.html Image Processing Resources http://eleceng.ukc.ac.uk/~rls3/Contents.htm Publications of Carsten Steger http://www9.informatik.tu-muenchen.de/people/steger/publications.html FAQs comp.dsp FAQ www.bdti.com/faq/dsp_faq.htm Robotics FAQ www.frc.ri.cmu.edu/robotics-faq Where's the sci.image.processing FAQ? www.cc.iastate.edu/olc_answers/packages/graphics/sci.image.processing.faq.html comp.graphics.algorithms FAQ, Section 3, 2D Image/Pixel Computations www.exaflop.org/docs/cgafaq Astronomical Image Processing System FAQ www.cv.nrao.edu/aips/aips_faq.html
作图像处理方面的研究工作,最重要的两个问题:其一是要把握住国际上最前沿的内容;其二是所作工作要具备很高的实用背景。解决第一个问题的办法就是找出这个方向公认最牛的几个超级大拿(看看他们都在作什么)和最权威的出版物(阅读上面最新的文献),解决第二个问题的办法是你最好能够找到一个实际应用的项目,边做边写文章。 做好这几点的途径之一就是充分利用网络资源,特别是权威网站和大拿们的个人主页。下面是我收集的一些资源,希望对大家有用. 研究群体 大拿主页 前沿期刊 GPL软件资源 搜索引擎 一、研究群体 http://www-2.cs.cmu.edu/~cil/vision.html 这是卡奈基梅隆大学的计算机视觉研究组的主页,上面提供很全的资料,从发表文章的下载到演示程序、测试图像、常用链接、相关软硬件,甚至还有一个搜索引擎。 http://www.cmis.csiro.au/IAP/zimage.htm 这是一个侧重图像分析的站点,一般。但是提供一个Image Analysis环境---ZIMAGE and SZIMAGE。 http://www.via.cornell.edu/ 康奈尔大学的计算机视觉和图像分析研究组,好像是电子和计算机工程系的。侧重医学方面的研究,但是在上面有相当不错资源,关键是它正在建设中,能够跟踪一些信息。 http://www2.parc.com/istl/groups/did/didoverview.shtml 有一个很有意思的项目:DID(文档图像解码)。 http://www-cs-students.stanford.edu/ 斯坦福大学计算机系主页,自己找吧:( http://www.fmrib.ox.ac.uk/analysis/ 主要研究:Brain Extraction Tool,Nonlinear noise reduction,Linear Image Registration, Automated Segmentation,Structural brain change analysis,motion correction,etc. http://www.cse.msu.edu/prip/ 这是密歇根州立大学计算机和电子工程系的模式识别--图像处理研究组,它的FTP上有许多的文章(NEW)。 http://pandora.inf.uni-jena.de/p/e/index.html 德国的一个数字图像处理研究小组,在其上面能找到一些不错的链接资源。 http://www-staff.it.uts.edu.au/~sean/CVCC.dir/home.html CVIP(used to be CVCC for Computer Vision and Cluster Computing) is a research group focusing on cluster-based computer vision within the Spiral Architecture. http://cfia.gmu.edu/ The mission of the Center for Image Analysis is to foster multi-disciplinary research in image, multimedia and related technologies by establishing links between academic institutes, industry and government agencies, and to transfer key technologies to help industry build next generation commercial and military imaging and multimedia systems. http://peipa.essex.ac.uk/info/groups.html 可以通过它来搜索全世界各地的知名的计算机视觉研究组(CV Groups),极力推荐。 二、图像处理GPL库 http://www.ph.tn.tudelft.nl/~klamer/cppima.html Cppima 是一个图像处理的C++函数库。这里有一个较全面介绍它的库函数的文档,当然你也可以下载压缩的GZIP包,里面包含TexInfo格式的文档。 http://iraf.noao.edu/ Welcome to the IRAF Homepage! IRAF is the Image Reduction and Analysis Facility, a general purpose software system for the reduction and analysis of astronomical data. http://entropy.brni-jhu.org/tnimage.html 一个非常不错的Unix系统的图像处理工具,看看它的截图。你可以在此基础上构建自己的专用图像处理工具包。 http://sourceforge.net/projects/ 这是GPL软件集散地,到这里找你想要得到的IP库吧。 三、搜索资源 当然这里基本的搜索引擎还是必须要依靠的,比如Google等,可以到我常用的链接看看。下面的链接可能会节省你一些时间: http://sal.kachinatech.com/ http://cheminfo.pku.edu.cn/mirrors/SAL/index.shtml 四、大拿网页 http://www.ai.mit.edu/people/wtf/ 这位可是MIT人工智能实验室的BILL FREEMAN。大名鼎鼎!专长是:理解--贝叶斯模型。 http://www.merl.com/people/brand/ MERL(Mitsubishi Electric Research Laboratory)中的擅长“Style Machine”高手。 http://research.microsoft.com/~ablake/ CV界极有声望的A.Blake 1977年毕业于剑桥大学三一学院并或数学与电子科学学士学位。之后在MIT,Edinburgh,Oxford先后组建过研究小组并成为Oxford的教授,直到1999年进入微软剑桥研究中心。主要工作领域是计算机视觉。 http://www-2.cs.cmu.edu/afs/cs.cmu.edu/user/har/Web/home.html 这位牛人好像正在学习汉语,并且搜集了诸如“两只老虎(Two Tigers)”的歌曲,嘿嘿:) 他的主页上面还有几个牛:Shumeet Baluja, Takeo Kanade。他们的Face Detection作的绝对是世界一流。他毕业于卡奈基梅隆大学的计算机科学系,兴趣是计算机视觉。 http://www.ifp.uiuc.edu/yrui_ifp_home/html/huang_frame.html 这位老牛在1963年就获得了MIT的博士学位!他领导的Image Lab比较出名的是指纹识别。 -------------------------------------------------------------------------------- 下面这些是我搜集的牛群(大部分是如日中天的Ph.D们),可以学习的是他们的Study Ways! Finn Lindgren(Sweden):Statistical image analysis http://www.maths.lth.se/matstat/staff/finn/ Pavel Paclik(Prague):statistical pattern recognition http://www.ph.tn.tudelft.nl/~pavel/ Dr. Mark Burge:machine learning and graph theory http://cs.armstrong.edu/burge/ yalin Wang:Document Image Analysis http://students.washington.edu/~ylwang/ Geir Storvik: Image analysis http://www.math.uio.no/~geirs/ Heidorn http://alexia.lis.uiuc.edu/~heidorn/ Joakim Lindblad:Digital Image Cytometry http://www.cb.uu.se/~joakim/index_eng.html S.Lavirotte: http://www-sop.inria.fr/cafe/Stephane.Lavirotte/ Sporring: scale-space techniques http://www.lab3d.odont.ku.dk/~sporring/ Mark Jenkinson:Reduction of MR Artefacts http://www.fmrib.ox.ac.uk/~mark/ Justin K. Romberg:digital signal processing http://www-dsp.rice.edu/~jrom/ Fauqueur:Image retrieval by regions of interest http://www-rocq.inria.fr/~fauqueur/ James J. Nolan:Computer Vision http://cs.gmu.edu/~jnolan/ Daniel X. Pape:Information http://www.bucho.org/~dpape/ Drew Pilant:remote sensing technology http://www.geo.mtu.edu/~anpilant/index.html 五、前沿期刊(TOP10) 这里的期刊大部分都可以通过上面的大拿们的主页间接找到,在这列出主要是为了节省直接想找期刊投稿的兄弟的时间:) IEEE Trans. On PAMI http://www.computer.org/tpami/index.htm IEEE Transactionson Image Processing http://www.ieee.org/organizations/pubs/transactions/tip.htm Pattern Recognition http://www.elsevier.com/locate/issn/00313203 Pattern Recognition Letters http://www.elsevier.com/locate/issn/01678655 神经网络 Neural Networks Tutorial Review http://hem.hj.se/~de96klda/NeuralNetworks.htm ftp://ftp.sas.com/pub/neural/FAQ.html Image Compression with Neural Networks http://www.comp.glam.ac.uk/digimaging/neural.htm Backpropagator's Review http://www.dontveter.com/bpr/bpr.html Bibliographies on Neural Networks http://liinwww.ira.uka.de/bibliography/Neural/ Intelligent Motion Control with an Artificial Cerebellum http://www.q12.org/phd.html Kernel Machines http://www.kernel-machines.org/ Some Neural Networks Research Organizations http://www.ieee.org/nnc/ http://www.inns.org/ Neural Network Modeling in Vision Research http://www.rybak-et-al.net/nisms.html Neural Networks and Machine Learning http://learning.cs.toronto.edu/ Neural Application Software http://attrasoft.com Neural Network Toolbox for MATLAB http://www.mathworks.com/products/neuralnet/ Netlab Software http://www.ncrg.aston.ac.uk/netlab/ Kunama Systems Limited http://www.kunama.co.uk/ Computer Vision Computer Vision Homepage, Carnegie Mellon University www.cs.cmu.edu/~cil/vision.html Annotated Computer Vision Bibliography http://iris.usc.edu/Vision-Notes/bibliography/contents.html http://iris.usc.edu/Vision-Notes/rosenfeld/contents.html Lawrence Berkeley National Lab Computer Vision and Robotics Applications http://www-itg.lbl.gov/ITG.hm.pg.docs/VISIon/vision.html CVonline by University of Edinburgh The Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision, www.dai.ed.ac.uk/CVonline Computer Vision Handbook, www.cs.hmc.edu/~fleck/computer-vision-handbook Vision Systems Courseware www.cs.cf.ac.uk/Dave/Vision_lecture/Vision_lecture_caller.html Research Activities in Computer Vision http://www-syntim.inria.fr/syntim/analyse/index-eng.html Vision Systems Acronyms www.vision-systems-design.com/vsd/archive/acronyms.html Dictionary of Terms in Human and Animal Vision http://cns-web.bu.edu/pub/laliden/WWW/Visionary/Visionary.html Metrology based on Computer Vision www.cranfield.ac.uk/sme/amac/research/metrology/metrology.html Digital Photography Digital Photography, Scanning, and Image Processing www.dbusch.com/scanners/scanners.html Educational Resources, Universities Center for Image Processing in Education www.cipe.com Library of Congress Call Numbers Related to Imaging Science by Rochester Institute of Technology http://wally2.rit.edu/pubs/guides/imagingcall.html Mathematical Experiences through Image Processing, University of Washington www.cs.washington.edu/research/metip/metip.html Vismod Tech Reports and Publications, MIT http://vismod.www.media.mit.edu/cgi-bin/tr_pagemaker Vision Lab PhD dissertation list, University of Antwerp http://wcc.ruca.ua.ac.be/~visielab/theses.html INRIA (France) Research Projects: Human-Computer Interaction, Image Processing, Data Management, Knowledge Systems www.inria.fr/Themes/Theme3-eng.html Image Processing Resources http://eleceng.ukc.ac.uk/~rls3/Contents.htm Publications of Carsten Steger http://www9.informatik.tu-muenchen.de/people/steger/publications.html FAQs comp.dsp FAQ www.bdti.com/faq/dsp_faq.htm Robotics FAQ www.frc.ri.cmu.edu/robotics-faq Where's the sci.image.processing FAQ? www.cc.iastate.edu/olc_answers/packages/graphics/sci.image.processing.faq.html comp.graphics.algorithms FAQ, Section 3, 2D Image/Pixel Computations www.exaflop.org/docs/cgafaq Astronomical Image Processing System FAQ www.cv.nrao.edu/aips/aips_faq.html
GuiLin|China MIPPR | Nav: Registration | Conference | Travel/General | Accepted/Rejected +Abstracts Submission +Paper Submission +Accepted/Rejected +Conferences +Travel/General +Committees +Investment Cooperation +Contact In 2009,the sixth International Symposium on Multispectral Image Processing and Pattern Recognition was held in Yichang, China.This symposium was a great success. Scientists, engineers, and graduate students from more than 20 countries presented over 280 talks conveying research results in image processing and pattern recognition. 697 papers were selected for publication in SPIE proccedings. After that,the seventh SPIE International Symposium on Multispectral Image Processing and Pattern Recogniton(MIPPR'2011) will be held on November 4,2011 in the historical city of Guilin,China. Guilin is in the north of Guangxi.The population in the city of Guilin is more than six hundred thousand. There are famous and beautiful sceneries in Guilin,such as Li River, Elephant Trunk Hill and so on. The conference will bring together scientists,professoes,engineers and graduate students in this field and provide a forum for presentation,exchange and discussion of recent advances in theory,techniques,algorithms and applications in Multisepctral Image Processing and Pattern Recognition.In order to better inform the participants of the latest developments in the different branches of multispectral image processing and pattern recognition,apart from general papers to be presented at the forthcoming conference,we shall organize several special plenary sections for top quality invited papers. Sponsored by National Key Laboratory of Science and Technology on Multi-spectral Information Processing (China) Huazhong University of Science and Technology (China) SPIE- The international society advancing light-based research (USA) Guilin University of Electronic Technology (China) Symposium Honorary Chair: Bo Zhang, Tsinghua University (China) Symposium Chair: M.V.Srinivasan, University of Queensland (Australia) Deren Li,Wuhan University (China) Porgram Committee Chairs: Bir Bhanu, The University of California at Riverside (USA) Supported by: National Natural Sci. Foundation of China Education Ministry of China Proceedings Publisher: SPIE an international society advancing an interdisciplinary approach to the science and application of light.(USA) Organizing Committee Chair: Jianguo Liu,Huazhong University of Science and Technology (China) Co-Chairs: Jinxue Wang, SPIE (USA) General Secretary: Faxiong Zhang ,Huazhong University of Science and Technology (China) Asociate General Secretary: Wenwen Gu, Huazhong University of Science and Technology (China) what's new? | submit site | search | about us | gbook | Style Like Exp... ImageProcessing Art. IPRAI 2011 All Right Reserved. Designed and Programed by Chengzhao 会议网址: http://iprai.hust.edu.cn/mippr/default.html
数字图像处理领域可以投稿的期刊 Computer Vision and Image Processing IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) IEEE International Journal of Computer Vision (IJCV) Springer Vision Research Elsevier IEEE Transactions on Image Processing (IEEE-T-IP) IEEE ACM Transactions on Applied Perception ACM Computer Vision and Image Understanding (CVIU) Elsevier Image and Vision Computing Elsevier Journal of Vision JV Journal of Visual Communication and Image Representation (JVCIR) Elsevier Journal of Mathematical Imaging and Vision Springer Journal of Electronic Imaging SPIE ICGST International Journal on Graphics, Vision and Image Processing (GVIP) ICGST MGV: Machine GRAPHICS VISION Institute of Computer Science International Journal of Imaging Systems and Technology Wiley InterScience Electronic Letters on Computer Vision and Image Analysis Elcvia The Visual Computer Springer IET Image Processing IET IET Computer Vision IET International Journal of Image and Graphics (IJIG) World Scientific International Journal of Remote Sensing Taylor Francis SIAM Journal on Imaging Sciences SIAM Signal, Image and Video Processing Springer Pattern Recognition Pattern Recognition Elsevier Pattern Recognition Letters (PRL) Elsevier International Journal of Pattern Recognition and Artificial Intelligence World Scientific Pattern Analysis Applications Springer Journal of Pattern Recognition Research (JPRR) JPRR Signal Processing IEEE Signal Processing Letters IEEE IEEE Signal Processing Magazine IEEE Signal Processing Elsevier EURASIP Journal on Applied Signal Processing EURASIP Signal Processing : Image Communication Elsevier IET Signal Processing IET Neurophysical Journals in Computer Vision Nature Neuroscience. Nature Visual Neuroscience. Cambridge IEEE Transactions on Neural Networks. IEEE Neural Networks Elsevier Perception and Psychophysics. Psychonomic Society Perception. Pion Ltd. Journal of Experimental Psychology: Human Perception and Performance. Elsevier Computer Graphics ACM Transactions on Graphics ACM IEEE Computer Graphics and Applications (CGA) IEEE IEEE Transactions on Visualization and Computer Graphics IEEE ACM SIGGRAPH Computer Graphics ACM Computers and Graphics Science Direct Computer Graphics Forum (including Eurographics) Eurographics Graphics Interface Graphics Interface Journal of Graphics Tools ACM Journal of Visualization and Computer Animation Wiley Symposium on Interactive 3D (I3D) ACM Virtual Reality Virtual Reality Software and Technology (VRST) ACM Machine Vision Applications Machine Vision and Applications Springer Real-Time Imaging Elsevier Vision Interface Vision Interface IEEE Transactions on Geoscience and Remote Sensing IEEE International Journal of Applied Earth Observation and Geoinformation Elsevier Remote Sensing of Environment Elsevier ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING ISPRS Journal of Applied Remote Sensing SPIE Journal of the Indian Society of Remote Sensing Springer Multimedia IEEE Transactions on Circuits and Systems for Video Technology IEEE IEEE Transactions on Multimedia IEEE Optics Journal Optical Society of America OSA Optometry and Vision Science LWW Information Fusion Information Fusion Elsevier Information Processing Letters Elsevier Information Sciences Elsevier Information Sciences - Applications Elsevier Information Systems Elsevier Soft Computing Applied Soft Computing Elsevier Journal of Soft Computing Springer Others Medical Image Analysis Elsevier ACM Transactions on Information Systems ACM Swarm Intelligence Springer IET Information Security IET Numerical Functional Analysis and Optimization Taylor Francis Sadhana - Academy Proceedings in Engineering Sciences Springer International Journal of Wavelets, Multiresolution and Information Processing (IJWMIP) World Scientific IETE Technical Review IETE IETE Journal of Research IETE IEEE Transactions on Information Forensics and Security IEEE
图像处理 来自:www.cybernet.sh.cn 举例说明在 Maple 读取和处理图像文件。 模型和原文献 » 下载 用户资源 中文资料下载 Maple 用户论坛 Maple 应用下载中心 Maple Primes - 在线支持 Maple 和 MapleSim 试用申请 Image Tools This example demonstrates how to efficiently work with images in Maple. Using the embedded GUI components you can read in images, apply manipulations and edge detection to those images.
2010 International Conference on Image Processing (ICIP 2010) 会议网址: http://www.icip2010.org/ 论文提交截止日期:2010年1月25日,录用通知:2010年4月26日 会议地点:中国香港,2010年9月12日2010年9月15日 这是IEEE Signal Processing Society主办的会议,从1994年开始ICIP基本是每年召开一次,ICMA 2010已是17届,每年会议均被EI、ISTP收录,每年的会议论文会选择部分论文到SCI收录期刊发表。 2008年15届ICIP会议被EI收录808篇、其中美国265篇、中国98篇、法国61篇、日本38篇、加拿大37篇、德国34篇、西班牙28篇、韩国26篇等。 中国科学院17篇、清华大学12篇、上海交通大学6篇、北京交通大学5篇、香港中文大学5篇、北京大学5篇、香港理工大学3篇、中山大学3篇、中国科技大学3篇、西安交通大学3篇、西安电子科技大学3篇等著名学校均在15届会议上发表论文。 会议主题: 1. IMAGE/VIDEO CODING AND TRANSMISSION: Still image and video coding, model-based and synthetic-natural hybrid coding, source/channel coding, stereoscopic and 3-D coding, coding standards, image and video over networks, and video streaming. 2. IMAGE/VIDEO PROCESSING AND ANALYSIS: Image filtering and enhancement, restoration, multiframe image restoration, video segmentation and tracking, wavelets and multiresolution processing, morphological processing, color and multispectral processing, stereoscopic and 3-D processing, modeling, analysis, biometrics, interpolation and super-resolution, motion detection and estimation, and computer vision. 3. IMAGE FORMATION: Biomedical imaging, remote sensing imaging, geophysical and seismic imaging, optical imaging, and synthetic-natural hybrid image systems. 4. IMAGE SCANNING, PRINTING, DISPLAY AND COLOR: Scanning and sampling, quantization and halftoning, color reproduction, image representation and rendering, display and printing systems, image quality assessment. 5. IMAGE/VIDEO STORAGE, RETRIEVAL, AND Authentication: Image and video databases, image search and sorting, video indexing and editing, integration of images and video with other media, content-based multimedia, multimedia applications, authentication and watermarking. 6. APPLICATIONS: Application of image processing technology to any field, including biomedical sciences, astronomy, geosciences, environment, humanities, and document processing.
人工智能网站和图像处理网络资源 (转载) 来源:互联网 酷勤网 收集 2009-02-21 摘要 酷勤网 图像处理研究工作的两个问题:其一是要把握住国际上最前沿的内容;其二是所作工作要具备很高的实用背景。解决第一个问题的办法就是找出这个方向公认最牛的几个超级大拿和最权威的出版物,解决第二个问题的办法是你最好能够找到一个实际应用的项目,边做边写文章。 第一部分:人工智能网站 科大人工智能实验室 网址: http://ailab.ai.ustc.edu.cn/ 图象识别与人工智能研究所 网址: http://iprai.hust.edu.cn/ 人工智能实验室 网址: http://www.aiport.net/ 人工智能历史 网址: http://www.longen.org/A-D/detaila~d/AIHistory.htm 神经网络在线 网址: http://www.2nsoft.com/ 人工神经网络首页 网址: http://www.youngfan.com/ann/index.htm 北邮模式识别与智能系统网站 网址: http://www.pris.edu.cn/ 复杂系统与计算智能实验室 网址: http://202.38.78.168/ 欧洲人工智能联合会ECCAI 说明:European Coordinating Committee for Artificial Intelligence 网址: http://www.eccai.org/ 国际人工智能联合会IJCAI 说明:IJCAI is the International Joint Conference on Artificial Intelligence, the main international gathering of researchers in AI. 网址: http://www.ijcai.org/ 美国人工智能联合会AAAI 说明:American Association for Artificial Intelligence (AAAI) devote to advancing the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines. 网址: http://www.aaai.org/ 第二部分:图像处理网络资源 作图像处理方面的研究工作,最重要的两个问题:其一是要把握住国际上最前沿的内容;其二是所作工作要具备很高的实用背景。解决第一个问题的办法就是找出这个方向公认最牛的几个超级大拿(看看他们都在作什么)和最权威的出版物(阅读上面最新的文献),解决第二个问题的办法是你最好能够找到一个实际应用的项目,边做边写文章。 做好这几点的途径之一就是充分利用网络资源,特别是权威网站和大拿们的个人主页。下面是我收集的一些资源,希望对大家有用。(这里我要感谢SMTH AI版的alamarik和Graphics版的faintt) 一、研究群体 cs.cmu.edu 这是卡奈基梅隆大学的计算机视觉研究组的主页,上面提供很全的资料,从发表文章的下载到演示程序、测试图像、常用链接、相关软硬件,甚至还有一个搜索引擎。 ZIMAGE 这是一个侧重图像分析的站点,一般。但是提供一个Image Analysis环境---ZIMAGE and SZIMAGE。 Conell.edu 康奈尔大学的计算机视觉和图像分析研究组,好像是电子和计算机工程系的。侧重医学方面的研究,但是在上面有相当不错资源,关键是它正在建设中,能够跟踪一些信息。 The statistical pattern and image analysis (SPIA) 有一个很有意思的项目:DID(文档图像解码)。 Stanford.edu 斯坦福大学计算机系主页,自己找吧:( Fmrib:Image Analysis Group 主要研究:Brain Extraction Tool,Nonlinear noise reduction,Linear Image Registration,Automated Segmentation,Structural brain change analysis,motion correction,etc. Pattern Recognition and Image Processing Lab 这是密歇根州立大学计算机和电子工程系的模式识别--图像处理研究组,它的FTP上有许多的文章(NEW)。 Pandora:Digital Image Processing Groups 德国的一个数字图像处理研究小组,在其上面能找到一些不错的 链接资源 。 CVCC:computer vision and image processing CVIP(used to be CVCC for Computer Vision and Cluster Computing) is a research group focusing on cluster-based computer vision within the Spiral Architecture. CFIA.gmu.edu:Multi-Disciplinary IA Research The mission of the Center for Image Analysis is to foster multi-disciplinary research in image, multimedia and related technologies by establishing links between academic institutes, industry and government agencies, and to transfer key technologies to help industry build next generation commercial and military imaging and multimedia systems. PEIPA 可以通过它来搜索全世界各地的知名的计算机视觉研究组(CV Groups),极力推荐。 二、图像处理GPL库 CPPima Cppima 是一个图像处理的C++函数库。这里有一个较全面介绍它的 库函数的文档 ,当然你也可以下载压缩的 GZIP包 ,里面包含TexInfo格式的文档。 IRAF Welcome to the IRAF Homepage! IRAF is the Image Reduction and Analysis Facility, a general purpose software system for the reduction and analysis of astronomical data. TNimage 一个非常不错的Unix系统的图像处理工具,看看 它的截图 。你可以在此基础上构建自己的专用图像处理工具包,我已经在计算机上成功安装了,看看 我运行的画面 。 SourceForge 这是GPL软件集散地,到这里找你想要得到的IP库吧。 三、搜索资源 当然这里基本的搜索引擎还是必须要依靠的,比如Google等,可以到 我常用的链接 看看。下面的链接可能会节省你一些时间: SAL(Scientific Applications on Linux) PKU's SAl Mirror 四、大拿网页 Bill Freeman 这位可是MIT人工智能实验室的BILL FREEMAN。大名鼎鼎!专长是:理解--贝叶斯模型。 Matthew Brand MERL(Mitsubishi Electric Research Laboratory)中的擅长Style Machine高手。 Andrew Blake CV界极有声望的A.Blake 1977年毕业于剑桥大学三一学院并或数学与电子科学学士学位。之后在MIT,Edinburgh,Oxford先后组建过研究小组并成为Oxford的教授,直到1999年进入微软剑桥研究中心。主要工作领域是计算机视觉。 Henry A. Rowley 这位牛人好像正在学习汉语,并且搜集了诸如两只老虎(Two Tigers)的歌曲,嘿嘿:) 他的主页上面还有几个牛:Shumeet Baluja, Takeo Kanade。他们的Face Detection作的绝对是世界一流。他毕业于卡奈基梅隆大学的计算机科学系,兴趣是计算机视觉。 Thomas Huang 这位老牛在1963年就获得了MIT的博士学位!他领导的Image Lab比较出名的是指纹识别。 下面这些是我搜集的牛群(大部分是如日中天的Ph.D们),可以学习的是他们的Study Ways! Finn Lindgren(Sweden):Statistical image analysis Pavel Paclik(Prague):statistical pattern recognition Dr. Mark Burge:machine learning and graph theory yalin Wang:Document Image Analysis Geir Storvik: Image analysis Heidorn Joakim Lindblad:Digital Image Cytometry S.Lavirotte: Sporring:scale-space techniques Mark Jenkinson:Reduction of MR Artefacts Justin K. Romberg:digital signal processing Fauqueur:Image retrieval by regions of interest James J. Nolan:Computer Vision Daniel X. Pape:Information Drew Pilant:remote sensing technology 五、前沿期刊(TOP10) 这里的期刊大部分都可以通过上面的大拿们的主页间接找到,在这列出主要是为了节省直接想找期刊投稿的兄弟的时间:) IEEE Trans. On PAMI IEEE Transactions on Image Processing Pattern Recognition Pattern Recognition Letters
作图像处理方面的研究工作,最重要的两个问题:其一是要把握住国际上最前沿的内容;其二是所作工作要具备很高的实用背景。解决第一个问题的办法就是找出这个方向公认最牛的几个超级大拿(看看他们都在作什么)和最权威的出版物(阅读上面最新的文献),解决第二个问题的办法是你最好能够找到一个实际应用的项目,边做边写文章。 做好这几点的途径之一就是充分利用网络资源,特别是权威网站和大拿们的个人主页。下面是我收集的一些资源,希望对大家有用. 研究群体 大拿主页 前沿期刊 GPL软件资源 搜索引擎 一、研究群体 http://www-2.cs.cmu.edu/~cil/vision.html 这是卡奈基梅隆大学的计算机视觉研究组的主页,上面提供很全的资料,从发表文章的下载到演示程序、测试图像、常用链接、相关软硬件,甚至还有一个搜索引擎。 http://www.cmis.csiro.au/IAP/zimage.htm 这是一个侧重图像分析的站点,一般。但是提供一个Image Analysis环境---ZIMAGE and SZIMAGE。 http://www.via.cornell.edu/ 康奈尔大学的计算机视觉和图像分析研究组,好像是电子和计算机工程系的。侧重医学方面的研究,但是在上面有相当不错资源,关键是它正在建设中,能够跟踪一些信息。 http://www2.parc.com/istl/groups/did/didoverview.shtml 有一个很有意思的项目:DID(文档图像解码)。 http://www-cs-students.stanford.edu/ 斯坦福大学计算机系主页,自己找吧:( http://www.fmrib.ox.ac.uk/analysis/ 主要研究:Brain Extraction Tool,Nonlinear noise reduction,Linear Image Registration, Automated Segmentation,Structural brain change analysis,motion correction,etc. http://www.cse.msu.edu/prip/ 这是密歇根州立大学计算机和电子工程系的模式识别--图像处理研究组,它的FTP上有许多的文章(NEW)。 http://pandora.inf.uni-jena.de/p/e/index.html 德国的一个数字图像处理研究小组,在其上面能找到一些不错的链接资源。 http://www-staff.it.uts.edu.au/~sean/CVCC.dir/home.html CVIP(used to be CVCC for Computer Vision and Cluster Computing) is a research group focusing on cluster-based computer vision within the Spiral Architecture. http://cfia.gmu.edu/ The mission of the Center for Image Analysis is to foster multi-disciplinary research in image, multimedia and related technologies by establishing links between academic institutes, industry and government agencies, and to transfer key technologies to help industry build next generation commercial and military imaging and multimedia systems. http://peipa.essex.ac.uk/info/groups.html 可以通过它来搜索全世界各地的知名的计算机视觉研究组(CV Groups),极力推荐。 二、图像处理GPL库 http://www.ph.tn.tudelft.nl/~klamer/cppima.html Cppima 是一个图像处理的C++函数库。这里有一个较全面介绍它的库函数的文档,当然你也可以下载压缩的GZIP包,里面包含TexInfo格式的文档。 http://iraf.noao.edu/ Welcome to the IRAF Homepage! IRAF is the Image Reduction and Analysis Facility, a general purpose software system for the reduction and analysis of astronomical data. http://entropy.brni-jhu.org/tnimage.html 一个非常不错的Unix系统的图像处理工具,看看它的截图。你可以在此基础上构建自己的专用图像处理工具包。 http://sourceforge.net/projects/ 这是GPL软件集散地,到这里找你想要得到的IP库吧。 三、搜索资源 当然这里基本的搜索引擎还是必须要依靠的,比如Google等,可以到我常用的链接看看。下面的链接可能会节省你一些时间: http://sal.kachinatech.com/ http://cheminfo.pku.edu.cn/mirrors/SAL/index.shtml 四、大拿网页 http://www.ai.mit.edu/people/wtf/ 这位可是MIT人工智能实验室的BILL FREEMAN。大名鼎鼎!专长是:理解--贝叶斯模型。 http://www.merl.com/people/brand/ MERL(Mitsubishi Electric Research Laboratory)中的擅长Style Machine高手。 http://research.microsoft.com/~ablake/ CV界极有声望的A.Blake 1977年毕业于剑桥大学三一学院并或数学与电子科学学士学位。之后在MIT,Edinburgh,Oxford先后组建过研究小组并成为Oxford的教授,直到1999年进入微软剑桥研究中心。主要工作领域是计算机视觉。 http://www-2.cs.cmu.edu/afs/cs.cmu.edu/user/har/Web/home.html 这位牛人好像正在学习汉语,并且搜集了诸如两只老虎(Two Tigers)的歌曲,嘿嘿:) 他的主页上面还有几个牛:Shumeet Baluja, Takeo Kanade。他们的Face Detection作的绝对是世界一流。他毕业于卡奈基梅隆大学的计算机科学系,兴趣是计算机视觉。 http://www.ifp.uiuc.edu/yrui_ifp_home/html/huang_frame.html 这位老牛在1963年就获得了MIT的博士学位!他领导的Image Lab比较出名的是指纹识别。 -------------------------------------------------------------------------------- 下面这些是我搜集的牛群(大部分是如日中天的Ph.D们),可以学习的是他们的Study Ways! Finn Lindgren(Sweden):Statistical image analysis http://www.maths.lth.se/matstat/staff/finn/ Pavel Paclik(Prague):statistical pattern recognition http://www.ph.tn.tudelft.nl/~pavel/ Dr. Mark Burge:machine learning and graph theory http://cs.armstrong.edu/burge/ yalin Wang:Document Image Analysis http://students.washington.edu/~ylwang/ Geir Storvik: Image analysis http://www.math.uio.no/~geirs/ Heidorn http://alexia.lis.uiuc.edu/~heidorn/ Joakim Lindblad:Digital Image Cytometry http://www.cb.uu.se/~joakim/index_eng.html S.Lavirotte: http://www-sop.inria.fr/cafe/Stephane.Lavirotte/ Sporring: scale-space techniques http://www.lab3d.odont.ku.dk/~sporring/ Mark Jenkinson:Reduction of MR Artefacts http://www.fmrib.ox.ac.uk/~mark/ Justin K. Romberg:digital signal processing http://www-dsp.rice.edu/~jrom/ Fauqueur:Image retrieval by regions of interest http://www-rocq.inria.fr/~fauqueur/ James J. Nolan:Computer Vision http://cs.gmu.edu/~jnolan/ Daniel X. Pape:Information http://www.bucho.org/~dpape/ Drew Pilant:remote sensing technology http://www.geo.mtu.edu/~anpilant/index.html 五、前沿期刊(TOP10) 这里的期刊大部分都可以通过上面的大拿们的主页间接找到,在这列出主要是为了节省直接想找期刊投稿的兄弟的时间:) IEEE Trans. On PAMI http://www.computer.org/tpami/index.htm IEEE Transactionson Image Processing http://www.ieee.org/organizations/pubs/transactions/tip.htm Pattern Recognition http://www.elsevier.com/locate/issn/00313203 Pattern Recognition Letters http://www.elsevier.com/locate/issn/01678655 神经网络 Neural Networks Tutorial Review http://hem.hj.se/~de96klda/NeuralNetworks.htm ftp://ftp.sas.com/pub/neural/FAQ.html Image Compression with Neural Networks http://www.comp.glam.ac.uk/digimaging/neural.htm Backpropagator's Review http://www.dontveter.com/bpr/bpr.html Bibliographies on Neural Networks http://liinwww.ira.uka.de/bibliography/Neural/ Intelligent Motion Control with an Artificial Cerebellum http://www.q12.org/phd.html Kernel Machines http://www.kernel-machines.org/ Some Neural Networks Research Organizations http://www.ieee.org/nnc/ http://www.inns.org/ Neural Network Modeling in Vision Research http://www.rybak-et-al.net/nisms.html Neural Networks and Machine Learning http://learning.cs.toronto.edu/ Neural Application Software http://attrasoft.com Neural Network Toolbox for MATLAB http://www.mathworks.com/products/neuralnet/ Netlab Software http://www.ncrg.aston.ac.uk/netlab/ Kunama Systems Limited http://www.kunama.co.uk/ Computer Vision Computer Vision Homepage, Carnegie Mellon University www.cs.cmu.edu/~cil/vision.html Annotated Computer Vision Bibliography http://iris.usc.edu/Vision-Notes/bibliography/contents.html http://iris.usc.edu/Vision-Notes/rosenfeld/contents.html Lawrence Berkeley National Lab Computer Vision and Robotics Applications http://www-itg.lbl.gov/ITG.hm.pg.docs/VISIon/vision.html CVonline by University of Edinburgh The Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision, www.dai.ed.ac.uk/CVonline Computer Vision Handbook, www.cs.hmc.edu/~fleck/computer-vision-handbook Vision Systems Courseware www.cs.cf.ac.uk/Dave/Vision_lecture/Vision_lecture_caller.html Research Activities in Computer Vision http://www-syntim.inria.fr/syntim/analyse/index-eng.html Vision Systems Acronyms www.vision-systems-design.com/vsd/archive/acronyms.html Dictionary of Terms in Human and Animal Vision http://cns-web.bu.edu/pub/laliden/WWW/Visionary/Visionary.html Metrology based on Computer Vision www.cranfield.ac.uk/sme/amac/research/metrology/metrology.html Digital Photography Digital Photography, Scanning, and Image Processing www.dbusch.com/scanners/scanners.html Educational Resources, Universities Center for Image Processing in Education www.cipe.com Library of Congress Call Numbers Related to Imaging Science by Rochester Institute of Technology http://wally2.rit.edu/pubs/guides/imagingcall.html Mathematical Experiences through Image Processing, University of Washington www.cs.washington.edu/research/metip/metip.html Vismod Tech Reports and Publications, MIT http://vismod.www.media.mit.edu/cgi-bin/tr_pagemaker Vision Lab PhD dissertation list, University of Antwerp http://wcc.ruca.ua.ac.be/~visielab/theses.html INRIA (France) Research Projects: Human-Computer Interaction, Image Processing, Data Management, Knowledge Systems www.inria.fr/Themes/Theme3-eng.html Image Processing Resources http://eleceng.ukc.ac.uk/~rls3/Contents.htm Publications of Carsten Steger http://www9.informatik.tu-muenchen.de/people/steger/publications.html FAQs comp.dsp FAQ www.bdti.com/faq/dsp_faq.htm Robotics FAQ www.frc.ri.cmu.edu/robotics-faq Where's the sci.image.processing FAQ? www.cc.iastate.edu/olc_answers/packages/graphics/sci.image.processing.faq.html comp.graphics.algorithms FAQ, Section 3, 2D Image/Pixel Computations www.exaflop.org/docs/cgafaq Astronomical Image Processing System FAQ www.cv.nrao.edu/aips/aips_faq.html