Cursive script recognition using wildcards and multiple experts

Hennig, A. and Sherkat, N., 2001. Cursive script recognition using wildcards and multiple experts. Pattern Analysis and Applications, 4 (1), pp. 51-60. ISSN 1433-7541

[img]
Preview
Text
196415_467 Sherkat PrePublisher.pdf

Download (208kB) | Preview

Abstract

Variability in handwriting styles suggests that many letter recognition engines cannot correctly identify some hand-written letters of poor quality at reasonable computational cost. Methods that are capable of searching the resulting sparse graph of letter candidates are therefore required. The method presented here employs ‘wildcards’ to represent missing letter candidates. Multiple experts are used to represent different aspects of handwriting. Each expert evaluates closeness of match and indicates its confidence. Explanation experts determine the degree to which the word alternative under consideration explains extraneous letter candidates. Schemata for normalisation and combination of scores are investigated and their performance compared. Hill climbing yields near-optimal combination weights that outperform comparable methods on identical dynamic handwriting data.

Item Type: Journal article
Description: The original publication is available at www.springerlink.com
Publication Title: Pattern Analysis and Applications
Creators: Hennig, A. and Sherkat, N.
Publisher: Springer-Verlag
Place of Publication: New York, N.Y.
Date: 2001
Volume: 4
Number: 1
ISSN: 1433-7541
Identifiers:
NumberType
10.1007/s100440170024DOI
Divisions: Schools > School of Science and Technology
Record created by: EPrints Services
Date Added: 09 Oct 2015 09:49
Last Modified: 23 Aug 2016 09:06
URI: https://irep.ntu.ac.uk/id/eprint/3243

Actions (login required)

Edit View Edit View

Views

Views per month over past year

Downloads

Downloads per month over past year