Fuzzy Cognitive Maps for stereovision matching

This paper outlines a method for solving the stereovision matching problem using edge segments as the primitives. In stereovision matching the following constraints are commonly used: epipolar, similarity, smoothness, ordering and uniqueness. We propose a new matching strategy under a fuzzy context in which such constraints are mapped. The fuzzy context integrates both Fuzzy Clustering and Fuzzy Cognitive Maps. With such purpose a network of concepts (nodes) is designed, each concept represents a pair of primitives to be matched. Each concept has associated a fuzzy value which determines the degree of the correspondence. The goal is to achieve high performance in terms of correct matches. The main findings of this paper are reflected in the use of the fuzzy context that allows building the network of concepts where the matching constraints are mapped. Initially, each concept value is loaded via the Fuzzy Clustering and then updated by the Fuzzy Cognitive Maps framework. This updating is achieved through the influence of the remainder neighboring concepts until a good global matching solution is achieved. Under this fuzzy approach we gain quantitative and qualitative matching correspondences. This method works as a relaxation matching approach and its performance is illustrated by comparative analysis against some existing global matching methods.

[1]  Jia-Guu Leu,et al.  Detecting the dislocations in metal crystals from microscopic images , 1990, Pattern Recognit..

[2]  T. Poggio,et al.  A computational theory of human stereo vision , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  R. J. Schalkoff,et al.  ANN Implementation of Stereo Vision Using a Multi-Layer Feedback Architecture , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[4]  Eric Backer,et al.  Finding point correspondences using simulated annealing , 1995, Pattern Recognit..

[5]  Yassine Ruichek,et al.  A neural matching algorithm for 3-D reconstruction from stereo pairs of linear images , 1996, Pattern Recognit. Lett..

[6]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Keith E. Price,et al.  Relaxation Matching Techniques-A Comparison , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[9]  Thomas S. Huang,et al.  Learning and Feature Selection in Stereo Matching , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  W. Eric L. Grimson,et al.  Computational Experiments with a Feature Based Stereo Algorithm , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Nasser M. Nasrabadi.  A Stereo Vision Technique Using Curve-Segments and Relaxation Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Zhengyou Zhang,et al.  New Measurements and Corner-Guidance for Curve Matching with Probabilistic Relaxation , 2002, International Journal of Computer Vision.

[14]  K. Ramesh Babu,et al.  Linear Feature Extraction and Description , 1979, IJCAI.

[15]  Stephen T. Barnard,et al.  Stochastic stereo matching over scale , 1989, International Journal of Computer Vision.

[16]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[17]  Gonzalo Pajares,et al.  A new learning strategy for stereo matching derived from a fuzzy clustering method , 2000, Fuzzy Sets Syst..

[18]  Shuichi Tanaka,et al.  A rule-based approach to binocular stereopsis , 1988 .

[19]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[20]  An Luo,et al.  A new multilevel line-based stereo vision algorithm based on fuzzy techniques , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[21]  Mohan M. Trivedi,et al.  Region-based stereo analysis for robotic applications , 1989, IEEE Trans. Syst. Man Cybern..

[22]  QianSheng Cheng,et al.  The stability problem for fuzzy bidirectional associative memories , 2002, Fuzzy Sets Syst..

[23]  Kim L. Boyer,et al.  Robust Contour Decomposition Using a Constant Curvature Criterion , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Gonzalo Pajares,et al.  Stereo matching using Hebbian learning , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[25]  Zezhi Chen,et al.  Image dense matching based on region growth with adaptive window , 2002, Pattern Recognit. Lett..

[26]  Anil K. Jain,et al.  Analysis and Interpretation of Range Images , 1989, Springer Series in Perception Engineering.

[27]  D Marr,et al.  A computational theory of human stereo vision. , 1979, Proceedings of the Royal Society of London. Series B, Biological sciences.

[28]  Gonzalo Pajares Martinsanz,et al.  Stereovision matching through support vector machines , 2003 .

[29]  Gonzalo Pajares Martinsanz,et al.  On combining support vector machines and simulated annealing in stereovision matching , 2004 .

[30]  Nasser M. Nasrabadi,et al.  Hopfield network for stereo vision correspondence , 1992, IEEE Trans. Neural Networks.

[31]  Eric Paul Krotkov,et al.  Active Computer Vision by Cooperative Focus and Stereo , 1989, Springer Series in Perception Engineering.

[32]  Gonzalo Pajares,et al.  Relaxation labeling in stereo image matching , 2000, Pattern Recognit..

[33]  Filiberto Pla,et al.  Dealing with segmentation errors in region-based stereo matching , 2000, Pattern Recognit..

[34]  Gérard G. Medioni,et al.  Detection of Intensity Changes with Subpixel Accuracy Using Laplacian-Gaussian Masks , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Francisco Casacuberta Nolla.  Redes Neuronales Artificiales , 1998 .

[36]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[37]  Ramakant Nevatia,et al.  Segment-based stereo matching , 1985, Comput. Vis. Graph. Image Process..

[38]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[39]  X. B. Olabe.  Redes Neuronales Artificiales y sus Aplicaciones , 2008 .

[40]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[41]  Gonzalo Pajares,et al.  The non-parametric Parzen's window in stereo vision matching , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[42]  Yeong-Ho Ha,et al.  Iterative relaxational stereo matching based on adaptive support between disparities , 1998, Pattern Recognit..

[43]  Bart Kosko,et al.  Fuzzy Cognitive Maps , 1986, Int. J. Man Mach. Stud..

[44]  William J. Christmas,et al.  Structural Matching in Computer Vision Using Probabilistic Relaxation , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  J. M. M. Montiel,et al.  Indoor robot motion based on monocular images , 2001, Robotica.

[46]  Yeong-Ho Ha,et al.  Hybrid stereo matching with a new relaxation scheme of preserving disparity discontinuity , 2000, Pattern Recognit..

[47]  Dong Hyun Kim,et al.  Analysis of quantization error in line-based stereo matching , 1994, Pattern Recognit..

[48]  Tomaso Poggio,et al.  A Theory of Human Stereo Vision , 1977 .

[49]  Gonzalo Pajares,et al.  Relaxation by Hopfield network in stereo image matching , 1998, Pattern Recognit..