Lexicon-driven handwritten word recognition using optimal linear combinations of order statistics

Authors
Chen, WT Gader, P Shi, HC
Citation
Wt. Chen et al., Lexicon-driven handwritten word recognition using optimal linear combinations of order statistics, IEEE PATT A, 21(1), 1999, pp. 77-82
Citations number
31
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN journal
01628828 → ACNP
Volume
21
Issue
1
Year of publication
1999
Pages
77 - 82
Database
ISI
SICI code
0162-8828(199901)21:1<77:LHWRUO>2.0.ZU;2-J
Abstract
In the standard segmentation-based approach to handwritten word recognition , individual character-class confidence scores are combined via averaging t o estimate confidences in the hypothesized identities for a word. We descri be a methodology for generating optimal Linear Combination of Order Statist ics operators for combining character class confidence scores. Experimental results are provided on over 1,000 word images.