A stroke-based neuro-fuzzy system for handwritten chinese character recognition

In this article, a stroke-based neuro-fuzzy system for off-line recognition of handwritten Chinese characters is proposed. The system consists of three main components: stroke extraction, feature extraction, and recognition. Stroke extraction applies a run-length-based method to extract strokes from the image of a given character. Various fuzzy features of the extracted strokes, including slope, length, location, and cross relation, are obtained by the feature extraction module. An ART-based neural network, using a two-stage training algorithm, is used to recognize characters. This system extracts strokes in only two passes, and is free from the presence of spurious and thick strokes. The neural model used provides a fast convergence rate. Nodes are allowed to be shared to reduce the size of the resulting network. Features need not be classified in advance by the user. Furthermore, the architecture of the network is self-constructed without the intervention of the user. Experiments have shown that this system is effective.

[1]  Daniel S. Yeung,et al.  A fuzzy substroke extractor for handwritten Chinese characters , 1996, Pattern Recognit..

[2]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks. I. Classification , 1992, IEEE Trans. Neural Networks.

[3]  Lin-Yu Tseng,et al.  A stroke extraction method for multifont Chinese characters based on the reduced special interval graph , 1995, IEEE Trans. Syst. Man Cybern..

[4]  Paul Y. S. Cheung,et al.  Fuzzy-attribute graph with application to Chinese character recognition , 1992, IEEE Trans. Syst. Man Cybern..

[5]  Chang-Fuu Chen,et al.  Stroke extraction for chinese characters using a trend-followed transcribing technique , 1996, Pattern Recognit..

[6]  David S. Touretzky,et al.  Optical Chinese character recognition using probabilistic neural networks , 1997, Pattern Recognit..

[7]  Wen-Hsiang Tsai,et al.  Recognizing Handwritten Chinese Characters by Stroke-Segment Matching using an Iteration Scheme , 1991, Int. J. Pattern Recognit. Artif. Intell..

[8]  Hong Yan,et al.  Analysis of stroke structures of handwritten Chinese characters , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[9]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[10]  Jhing-Fa Wang,et al.  A robust Stroke Extraction method for Handwritten Chinese Characters , 1994, Document Image Analysis.

[11]  Hong Yan,et al.  Recognition of handwritten digits based on contour information , 1998, Pattern Recognit..

[12]  Zen Chen,et al.  Handwritten Chinese Character Recognition Using Stroke Structural Sequence Code , 1997, Journal of information science and engineering.

[13]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1988, Computer.

[14]  Hongwei Hao,et al.  Handwritten Chinese character recognition by metasynthetic approach , 1997, Pattern Recognit..

[15]  Ching Y. Suen,et al.  Application of a Multilayer Decision Tree in Computer Recognition of Chinese Characters , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Kuo-Chin Fan,et al.  A Stroke-Based Handwritten Chinese Character Recognition System Using Greedy Matching Method , 1995, Journal of information science and engineering.

[17]  Kuo-Chin Fan,et al.  Peripheral and global features for use in coarse classification of Chinese characters , 1997, Pattern Recognit..

[18]  Liliane Peters,et al.  Fuzzy feature description of handwriting patterns , 1997, Pattern Recognit..

[19]  Suh-Yin Lee,et al.  On-line signature verification using LPC cepstrum and neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[20]  Hang Joon Kim,et al.  On-line recognition of handwritten chinese characters based on hidden markov models , 1997, Pattern Recognit..

[21]  R.P. Lippmann,et al.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[22]  Fang-Hsuan Cheng.  Multi-stroke relaxation matching method for handwritten chinese character recognition , 1998, Pattern Recognit..

[23]  Din-Chang Tseng,et al.  Invariant handwritten Chinese character recognition using fuzzy min-max neural networks , 1997, Pattern Recognit. Lett..

[24]  Y. S. Cheung,et al.  A knowledge-based stroke-matching method for Chinese character recognition , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[25]  Fumitaka Kimura,et al.  Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[27]  Fang-Hsuan Cheng,et al.  Recognition of handprinted chinese characters via stroke relaxation , 1993, Pattern Recognit..

[28]  Nabil Jean Naccache,et al.  SPTA: A proposed algorithm for thinning binary patterns , 1984, IEEE Transactions on Systems, Man, and Cybernetics.

[29]  Kazumi Odaka,et al.  On-Line Cursive Kanji Character Recognition Using Stroke-Based Affine Transformation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  P. K. Simpson.  Fuzzy Min-Max Neural Networks-Part 1 : Classification , 1992 .