Title :
Contextual vector quantization modeling of hand-printed Chinese character recognition
Author :
Leung, S.-L. ; Chee, P.-C. ; Chan, C. ; Huo, Q.
Author_Institution :
Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
Abstract :
A hand-printed Chinese character recognizer based on contextual vector quantization (CVQ) has been built. The idea of CVQ is to quantize each pixel to a codeword by considering not just the pixel itself but its neighbors and their codeword identities as well. 100 samples of each character are collected from 100 writers, among them, 92 are used for training and 8 for testing. The characters are scanned by a 300 dpi scanner, which are then noise removed, thinned, segmented and size normalized. Stroke counts and segment strengths are adopted as observation features. For a vocabulary of 470 simplified Chinese characters, a recognition rate of 97% is achieved
Keywords :
handwriting recognition; image coding; image segmentation; optical character recognition; vector quantisation; CVQ; character segmentation; codeword; codeword identities; contextual vector quantization; hand printed Chinese character recognition; noise removal; observation features; pixel; recognition rate; scanner; segment strengths; size normalization; stroke counts; testing; training; Character recognition; Computer science; Context modeling; Hidden Markov models; Image recognition; Pattern recognition; Pixel; Speech recognition; Stochastic processes; Vector quantization;
Conference_Titel :
Image Processing, 1995. Proceedings., International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-8186-7310-9
DOI :
10.1109/ICIP.1995.537664
