Title :
Handwritten Chinese address recognition
Author :
Wang, Chunheng ; Hotta, Yoshinobu ; Suwa, Misako ; Naoi, Satoshi
Author_Institution :
Fujitsu R&D Center Co. Ltd., Beijing, China
Abstract :
A handwritten Chinese address recognition (HCAR) system is proposed in this paper. Handwritten Chinese address recognition is a difficult problem. Handwritten Chinese characters are characterized by large vocabulary, complicate structure, irregular distortion and touching characters etc. The proposed approach takes good advantage of Chinese address knowledge, and applies key character extraction and holistic word matching to solving the problem. Different from conventional approach, proposed approach can avoid the character segmentation error successfully. Experimental results show the proposed approach is very effective.
Keywords :
handwritten character recognition; natural languages; word processing; Chinese address knowledge; character segmentation error; complicate structure; handwritten Chinese address recognition; handwritten Chinese characters; holistic word matching; irregular distortion; key character extraction; large vocabulary; touching characters; Character recognition; Conferences; Handwriting recognition; Image recognition; Image segmentation; Laboratories; Research and development; Vocabulary;
Conference_Titel :
Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on
Print_ISBN :
0-7695-2187-8
DOI :
10.1109/IWFHR.2004.55