Applications of Self-Organization Networks Spatially Isomorphic to Patterns

A new technique based on self-organization is proposed for classifying patterns (which include characters, and two- and three-dimensional objects). A neuronal network, created to be a physical replica of each exemplar, is mapped onto the given test pattern by self-organization, during which the network undergoes deformation in an attempt to match the given test pattern. The extent of deformation is inversely proportional to the correctness of the match: smaller the deformation, better is the match. A deformation measure is proposed, leading to the classification of the test pattern. Also presented are some algorithmic improvements (including the choice of other deformation measures) to speed up computation. Examples illustrate the versatility of the technique.

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

[2]  K Fukushima,et al.  Handwritten alphanumeric character recognition by the neocognitron , 1991, IEEE Trans. Neural Networks.

[3]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[4]  M. Teague.  Image analysis via the general theory of moments , 1980 .

[5]  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.

[6]  Roland T. Chin,et al.  One-Pass Parallel Thinning: Analysis, Properties, and Quantitative Evaluation , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Y. V. Venkatesh,et al.  Modified neocognitron for improved 2-D pattern recognition , 1996 .

[8]  Gary E. Ford,et al.  Network model for invariant object recognition , 1994, Pattern Recognit. Lett..

[9]  Roland T. Chin,et al.  Analysis of Thinning Algorithms Using Mathematical Morphology , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Paulo J. G. Lisboa,et al.  Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers , 1992, IEEE Trans. Neural Networks.

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

[12]  Basil G. Mertzios,et al.  Shape recognition with a neural classifier based on a fast polygon approximation technique , 1994, Pattern Recognit..

[13]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[14]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[15]  Murali M. Menon,et al.  Classification of patterns using a self-organizing neural network , 1988, Neural Networks.

[16]  Etienne Barnard,et al.  Shift invariance and the neocognitron , 1990, Neural Networks.