Contextual vector quantization modeling of hand-printed Chinese character recognition
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 432-435
- https://doi.org/10.1109/icip.1995.537664
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
This publication has 6 references indexed in Scilit:
- A structural approach to online Chinese character recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Contextual vector quantization for speech recognition with discrete hidden Markov modelPattern Recognition, 1995
- A THINNING ALGORITHM BASED ON THE FORCE BETWEEN CHARGED PARTICLESSeries in Machine Perception and Artificial Intelligence, 1994
- Machine vision for keyword spotting using pseudo 2D hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Connected and degraded text recognition using planar hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- The automatic recognition of handprinted Chinese characters — A method of extracting an ordered sequence of strokesPattern Recognition Letters, 1983