Improved handwritten digit recognition system based on fuzzy rules and prototypes created by Euclidean distance

A method is developed to classify handwritten numbers based on prototypes created using Euclidean distance, weighted voting among closest prototypes and fuzzy rules to solve confusions. The set of closest prototypes is determined by an acceptance distance. The fuzzy rules use specialized functions to measure characteristics on the handwritten digits to determine whether a digit belongs to a particular class. Classification performance is compared among following approaches: closest prototype, weighted voting including linear and exponential weighting, and voting plus fuzzy rules. The method is also compared to an algorithm based on a multilayer perceptron (MLP) network with augmented training. The best classification achieved was by voting plus fuzzy rules (96.3/spl plusmn/0.4% for 11 simulations). This result compares favorably with those obtained by MLP on the same testing database (94.6/spl plusmn/0.5%).

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

[2]  C.A. Perez,et al.  Improvements on handwritten digit recognition by genetic selection of neural network topology and by augmented training , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[3]  P. Nagabhushan,et al.  A three-dimensional neural network model for unconstrained handwritten numeral recognition: a new approach , 1998, Pattern Recognit..

[4]  Zheru Chi,et al.  Handwritten numeral recognition using self-organizing maps and fuzzy rules , 1995, Pattern Recognit..

[5]  Sung-Bae Cho,et al.  Neural-network classifiers for recognizing totally unconstrained handwritten numerals , 1997, IEEE Trans. Neural Networks.

[6]  Jung-Hsien Chiang,et al.  Neural and Fuzzy Methods in Handwriting Recognition , 1997, Computer.

[7]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[8]  Stamatios V. Kartalopoulos.  Neural Network Paradigms , 1996 .

[9]  Claudio A. Perez,et al.  Improvements on handwritten digit recognition by cooperation of modular neural networks , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[10]  Teuvo Kohonen,et al.  Learning vector quantization , 1998 .

[11]  C.A. Perez,et al.  Handwritten digit recognition based on prototypes created by Euclidean distance , 1999, Proceedings 1999 International Conference on Information Intelligence and Systems (Cat. No.PR00446).