Korean character recognition using a TDNN and an HMM

Abstract We present an on-line Korean character recognition method using a Time Delay Neural Network and a Hidden Markov Model. A TDNN is used to estimate a posteriori probabilities for graphemes in a character. An HMM aligns graphemes onto tentative graphemes, which are produced by heuristic segmentation points, using a modified Viterbi algorithm. The HMM contains statistic information, i.e., the frequencies of grapheme pairs and first consonants in the underlying language. We experiment on the proposed method with multi-writer cursive characters in a boxed input mode. Tests with untrained 22,500 on-line cursive characters show a recognition rate of 93.4% and speed of 1.37 s per character.

[1]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[2]  Xiaolin Li,et al.  Corner detection and shape classification of on-line handprinted kanji strokes , 1993, Pattern Recognit..

[3]  Seong-Whan Lee,et al.  A New Methodology for Gray-Scale Character Segmentation and Recognition , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Seong-Whan Lee,et al.  A new methodology for gray-scale character segmentation and recognition , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[5]  Jian Zhou,et al.  Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[7]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Y. Le Cun,et al.  Shortest path segmentation: a method for training a neural network to recognize character strings , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[9]  Hang Joon Kim,et al.  On-Line Recognition of Cursive Korean Characters Using Art-based Stroke Classification (Recognition of Cursive Korean Characters) , 1996, Int. J. Pattern Recognit. Artif. Intell..

[10]  Hang Joon Kim,et al.  Recognition-based segmentation of on-line cursive Korean characters , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

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

[12]  Alexander H. Waibel,et al.  NPen/sup ++/: a writer independent, large vocabulary on-line cursive handwriting recognition system , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[13]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.