Toward robust handwritten Kanji character recognition

Citation
T. Wakahara et Y. Kimura, Toward robust handwritten Kanji character recognition, PATT REC L, 20(10), 1999, pp. 979-990
Citations number
30
Language
INGLESE
art.tipo
Article
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
PATTERN RECOGNITION LETTERS
ISSN journal
0167-8655 → ACNP
Volume
20
Issue
10
Year of publication
1999
Pages
979 - 990
Database
ISI
SICI code
0167-8655(199910)20:10<979:TRHKCR>2.0.ZU;2-P
Abstract
This paper addresses the problem of establishing a robust methodology for h andwritten Kanji character recognition. First, existing techniques in Japan are critically surveyed to clarify the state-of-the-art and remaining prob lems. Second, new and promising approaches are discussed in the light of th e general field of pattern recognition technology. Third, as a promising ch allenge to distortion-tolerant shape matching, adaptive or category-depende nt shape normalization of handwritten characters using global/local affine transformation (GAT/LAT) as a general deformation model is described. (C) 1 999 Elsevier Science B.V. All rights reserved.