A connectionist system for learning and recognition of structures: Application to handwritten characters

A connectionist system for learning and recognition of structures is developed. The system is a cascade of two different modules, one for detecting linear structures (primitives) and the other for integrating these linear structures. A connectionist model implementing Hough transform has been used for the first module. The peaks in the Hough space are found by iterative verification method. A multilayered perceptron (four layers) with suitably chosen number of nodes and links has been used for the second module. As long as the size of the output layer of first module remains fixed (even if the size of input image changes), the same second module can be used and this is because the modules operate independently. The system performance is tested on handwritten Bengali character set.

[1]  Yao Yong.  Handprinted Chinese character recognition via neural networks , 1988, Pattern Recognit. Lett..

[2]  C. A. Murthy,et al.  A connectionist model for category perception: theory and implementation , 1993, IEEE Trans. Neural Networks.

[3]  David L. Waltz,et al.  Toward memory-based reasoning , 1986, CACM.

[4]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[5]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[6]  E. Dubois,et al.  Digital picture processing , 1985, Proceedings of the IEEE.

[7]  Prasanna G. Mulgaonkar,et al.  Matching three-dimensional objects using a relational paradigm , 1984, Pattern Recognit..

[8]  Lambert Schomaker,et al.  Using stroke- or character-based self-organizing maps in the recognition of on-line, connected cursive script , 1993, Pattern Recognit..

[9]  Geoffrey E. Hinton,et al.  Connectionist Architectures for Artificial Intelligence , 1990, Computer.

[10]  Sankar K. Pal,et al.  Matching of Structural Shape Descriptions with Hopfield Net , 1993, Int. J. Pattern Recognit. Artif. Intell..

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

[12]  Isabelle Guyon,et al.  Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.

[13]  T. Pavlidis,et al.  Fuzzy sets and their applications to cognitive and decision processes , 1977 .

[14]  Kim-Teng Lua,et al.  Recognizing chinese characters through interactive activation and competition , 1990, Pattern Recognit..

[15]  Kim L. Boyer,et al.  Robotic Manipulation Experiments Using Structural Stereopsis for 3D Vision , 1986, IEEE Expert.

[16]  Kim-Teng Lua,et al.  Chinese character classification using an adaptive resonance network , 1992, Pattern Recognit..

[17]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[18]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .

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

[20]  Robert M. Haralick,et al.  Organization of Relational Models for Scene Analysis , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

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