Multiple elastic modules for visual pattern recognition

Fast synaptic plasticity, used to associate topologically ordered features in an input image to those of previously learned objects, has been previously proposed as a possible model for object recognition (von der Malsburg & Bienenstock, 1987, Europhysics Letters, 3(11), 1243–1249). In this paper, it is argued that in addition to rapid link dynamics, fast receptive field size dynamics are necessary to automatically escape from poor local matches and also allow for simultaneous recognition of multiple objects. Furthermore, a feature locking mechanism with a properly designed hysteresis property is needed to handle complex, cluttered, and dynamic scenes. The multiple elastic modules (MEM) model, described in this paper, utilizes newly developed dynamics that locate and recognize a previously learned object based on expected spatial arrangement of local features. The MEM model can be viewed as using a deformable template of an object to search the input scene. Unlike many of the current artificial neural network models, the proposed MEM model attempts to capture many of the functions available in the biological visual system by providing mechanisms for: multi-model feature integration, generation and maintenance of focus of attention, multiresolution hierarchical searching, and top-down expectation driven processing coupled with bottom-up feature activation processing. In addition, the MEM dynamics, unlike similar template matching approaches (Konen et al., 1994, Neural Networks, 7(6/7), 1019–1030; Yuille et al., 1992, International Journal of Computer Vision, 8(2), 99–111), does not converge to false objects when there are no sufficiently familiar objects in the scene. The performance of the MEM model in detection and recognition of objects through a number of computer simulations is demonstrated.

[1]  K. Fukushima Neural network model for selective attention in visual pattern recognition and associative recall. , 1987, Applied optics.

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

[3]  C. von der Malsburg,et al.  Distortion invariant object recognition by matching hierarchically labeled graphs , 1989, International 1989 Joint Conference on Neural Networks.

[4]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[5]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Jean-Luc Gaudiot,et al.  Implementing regularly structured neural networks on the DREAM machine , 1995, IEEE Trans. Neural Networks.

[7]  S. Edelman,et al.  Explorations of Shape Space , 1995 .

[8]  Christoph von der Malsburg,et al.  Pattern recognition by labeled graph matching , 1988, Neural Networks.

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

[10]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[11]  Richard Durbin,et al.  An analogue approach to the travelling salesman problem using an elastic net method , 1987, Nature.

[12]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[13]  Petar D. Simic,et al.  Statistical mechanics as the underlying theory of ‘elastic’ and ‘neural’ optimisations , 1990 .

[14]  Michael A. Arbib,et al.  The metaphorical brain 2 - neural networks and beyond (2. ed.) , 1972 .

[15]  Nasser M. Nasrabadi,et al.  Object recognition by a Hopfield neural network , 1991, IEEE Trans. Syst. Man Cybern..

[16]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[17]  Petar D. Simic Constrained Nets for Graph Matching and Other Quadratic Assignment Problems , 1991, Neural Comput..

[18]  Hungwen Li,et al.  Reconfigurable Massively Parallel Computers , 1991 .

[19]  Elie Bienenstock,et al.  A neural network for the retrieval of superimposed connection patterns , 1987 .

[20]  Wolfgang Konen,et al.  A fast dynamic link matching algorithm for invariant pattern recognition , 1994, Neural Networks.