Novel design of neural networks for handwritten Chinese character recognition

Handwritten Chinese character recognition system invariably sue different image processing techniques to preprocess the input image before the main classification and recognition techniques are used. The authors proposed a different approach to the system philosophy of solving the handwritten Chinese character recognition problem for no preprocessing is necessary. The Chinese characters are treat as ideographs. The proposed system comprise of a Rough Classifier which control the different Fine Classifiers. Each classifier is an optimized artificial neural network using genetic algorithms. A reduced system has been implemented. The result shows that the proposed system has higher recognition rate than the similar systems reported and is more efficiency.

[1]  Arnold L. Knoll,et al.  Experiments with "Characteristic Loci" for Recognition of Handprinted Characters , 1969, IEEE Transactions on Computers.

[2]  Michihiko Minoh,et al.  A fast algorithm for the minimum distance classifier and its application to Kanji character recognition , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[3]  Luís B. Almeida,et al.  Acceleration Techniques for the Backpropagation Algorithm , 1990, EURASIP Workshop.

[4]  Jun S. Huang,et al.  Separating similar complex Chinese characters by Walsh transform , 1987, Pattern Recognit..

[5]  A. Khotanzad,et al.  Distortion invariant character recognition by a multi-layer perceptron and back-propagation learning , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Nei Kato,et al.  Large scale hand-written character recognition system using subspace method , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[7]  Malayappan Shridhar,et al.  High accuracy character recognition algorithm using fourier and topological descriptors , 1984, Pattern Recognit..

[8]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[9]  Jun Guo,et al.  Recognition of handwritten character database ETL9B using pattern transformation method , 1994, Systems and Computers in Japan.

[10]  Devil H. F. Yip,et al.  Application of artificial neural networks in sales forecasting , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[11]  Ch Leung,et al.  Chain-code transform for Chinese character recognition , 1985 .

[12]  Nei Kato,et al.  High Accuracy Recognition of ETL9B Using Exclusive Learning Neural Network-II : ELNET-II (Special Issue on Character Recognition and Document Understanding) , 1996 .

[13]  I-Chang Jou,et al.  A new feature extraction method by neural networks , 1990, IEEE International Symposium on Circuits and Systems.

[14]  William W. H. Yu,et al.  Classification of coffee using artificial neural network , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[15]  George Nagy,et al.  Recognition of Printed Chinese Characters , 1966, IEEE Trans. Electron. Comput..

[16]  Isabelle Guyon,et al.  Design of a neural network character recognizer for a touch terminal , 1991, Pattern Recognit..

[17]  N. D. Tucker,et al.  A two-step strategy for character recognition using geometrical moments , 1975 .