Pattern recognition by homomorphic graph matching using Hopfield neural networks

Abstract The application of the Hopfield neural network as a constraint satisfaction network for pattern recognition is investigated in this paper. Suitable energy and compatibility functions are introduced for pattern recognition by homomorphic attributed relational graph (ARG) matching. Although many computer vision problems have been traditionally formulated as combinatorial optimization problems, most of them can be reduced to that of finding the nearest local minimum of an objective function. In this paper, a novel network initialization strategy is applied to achieve the desired complexity reduction. Further, a method to verify and localize the hypotheses generated by the Hopfield network is also presented using an efficient pose clustering algorithm. The performance of the connectionist approach to pattern recognition by homomorphic relational graph matching is demonstrated using a number of line patterns, silhouette images and circle patterns.

[1]  Carsten Peterson,et al.  A New Method for Mapping Optimization Problems Onto Neural Networks , 1989, Int. J. Neural Syst..

[2]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[4]  Marc Rioux,et al.  Recognition and Shape Synthesis of 3-D Objects Based on Attributed Hypergraphs , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Chin-Tu Chen,et al.  Constraint satisfaction neural networks for image recognition , 1993, Pattern Recognit..

[6]  Stan Z. Li,et al.  Matching: Invariant to translations, rotations and scale changes , 1992, Pattern Recognit..

[7]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[8]  Bir Bhanu,et al.  Representation and Shape Matching of 3-D Objects , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[10]  Demetri Terzopoulos,et al.  The Computation of Visible-Surface Representations , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Wei-Chung Lin,et al.  A hierarchical multiple-view approach to three-dimensional object recognition , 1991, IEEE Trans. Neural Networks.

[12]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[13]  Thomas H. Reiss,et al.  The revised Fundamental Theorem of Moment Invariants , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[15]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[16]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[17]  Marc H. Raibert,et al.  Running With Symmetry , 1986 .

[18]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[19]  Behrooz Kamgar-Parsi,et al.  Simultaneous fitting of several planes to point sets using neural networks , 1990, Comput. Vis. Graph. Image Process..

[20]  George C. Stockman,et al.  Object recognition and localization via pose clustering , 1987, Comput. Vis. Graph. Image Process..

[21]  Xinhua Zhuang,et al.  Robust segmentation of noisy images using a neural network model , 1992, Image Vis. Comput..

[22]  David E. van den Bout,et al.  Graph partitioning using annealed neural networks , 1990, International 1989 Joint Conference on Neural Networks.

[23]  M. Hebert,et al.  The Representation, Recognition, and Locating of 3-D Objects , 1986 .

[24]  Bernd Radig,et al.  Image sequence analysis using relational structures , 1984, Pattern Recognit..

[25]  Alan L. Yuille,et al.  Generalized Deformable Models, Statistical Physics, and Matching Problems , 1990, Neural Computation.

[26]  Thomas Risse,et al.  Hough transform for line recognition: Complexity of evidence accumulation and cluster detection , 1989, Comput. Vis. Graph. Image Process..

[27]  Stan Z. Li,et al.  Toward 3D vision from range images: An optimization framework and parallel networks , 1991, CVGIP: Image Understanding.

[28]  Sim Heng Ong,et al.  Image reconstruction by a Hopfield neural network , 1993, Image Vis. Comput..

[29]  Robert J. Schalkoff,et al.  Pattern recognition - statistical, structural and neural approaches , 1991 .

[30]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[31]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  N. M. Nasrabadi,et al.  Object recognition based on graph matching implemented by a Hopfield-style neural network , 1989, International 1989 Joint Conference on Neural Networks.

[33]  Thomas C. Henderson,et al.  CAGD-Based Computer Vision , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[35]  Erkki Oja,et al.  Randomized hough transform (rht) : Basic mech-anisms, algorithms, and computational complexities , 1993 .

[36]  George C. Stockman,et al.  Matching Images to Models for Registration and Object Detection via Clustering , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.