Share Email Print

Proceedings Paper

Character recognition in a Japanese text recognition system
Author(s): Tao Hong; Geetha Srikantan; V. C. Zandy; Chi Fang; Sargur N. Srihari
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Cherry Blossom is a machine-printed Japanese document recognition system developed at CEDAR in past years. This paper focuses on the character recognition part of the system. for Japanese character classification, two feature sets are used in the system: one is the local stroke direction feature; another is the gradient, structural and concavity feature. Based on each of those features, two different classifiers are designed: one is the so-called minimum error subspace classifier; another is the fast nearest-neighbor (FNN) classifier. Although the original version of the FNN classifier uses Euclidean distance measurement, its new version uses both Euclidean distance and the distance calculation defined in the ME subspace method. This integration improved performance significantly. The number of character classes handled by those classifiers is about 3,300 (including alphanumeric, kana and level-1 Kanji JIS). Classifiers were trained and tested on 200 ppi character images from CEDAR Japanese character image CD-ROM.

Paper Details

Date Published: 7 March 1996
PDF: 12 pages
Proc. SPIE 2660, Document Recognition III, (7 March 1996); doi: 10.1117/12.234723
Show Author Affiliations
Tao Hong, SUNY/Buffalo (United States)
Geetha Srikantan, Hughes Information Technology Corp. (United States)
V. C. Zandy, Univ. of Wisconsin/Madison (United States)
Chi Fang, SUNY/Buffalo (United States)
Sargur N. Srihari, SUNY/Buffalo (United States)

Published in SPIE Proceedings Vol. 2660:
Document Recognition III
Luc M. Vincent; Jonathan J. Hull, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?