An off-line large vocabulary hand-written Chinese character recognizer

A n off-line hand-written Chinese character recognizer based on Contextual Vector Quantization (CVQ) supporting a vocabulary of 4,616 Chinese characters, alphanumerics and punctuation symbols has been reported. Trained with a sample for each character from each of 100 writers and tested on texts of 160,000 characters written by another 200 writers, the average recognition rate is 77.2%. Two statistical language models have been investigated in this study. Their performances in terms of their capabilities in upgrading the recognition rate by 8.8% and i2.0% respectively when used as post-processors of the recognizer will be reported in this paper.

• Type: Conference
• Year: 1997
• Where: ICIP
• Authors: Pak-Kwong Wong, Chorkin Chan
• Keywords: Average Recognition Rate, Chinese Character Recognizer, Contextual Vector Quantization, ICIP 1997, Image Processing