AUTOMATIC SCRIPT IDENTIFICATION FROM DOCUMENT IMAGES USING CLUSTER-BASED TEMPLATES

Authors
HOCHBERG J KELLY P THOMAS T KERNS L
Citation
J. Hochberg et al., AUTOMATIC SCRIPT IDENTIFICATION FROM DOCUMENT IMAGES USING CLUSTER-BASED TEMPLATES, IEEE transactions on pattern analysis and machine intelligence, 19(2), 1997, pp. 176-181
Citations number
9
Categorie Soggetti
Computer Sciences","Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on pattern analysis and machine intelligence → ACNP
ISSN journal
01628828
Volume
19
Issue
2
Year of publication
1997
Pages
176 - 181
Database
ISI
SICI code
0162-8828(1997)19:2<176:ASIFDI>2.0.ZU;2-D
Abstract
We describe an automated script identification system for typeset docu ment images. Templates for each script are created by clustering textu al symbols from a training set. Symbols from new images are compared t o the templates to find the best script. Our current system processes thirteen scripts with minimal preprocessing and high accuracy.