TextureforScriptIdentification.PDFVIP

Griffith Research Online .au Texture for Script Identification Author Busch, Andrew, W. Boles, Wageeh, Sridharan, Sridha Published 2005 Journal Title IEEE Transactions on Pattern Analysis and Machine Intelligence DOI /10.1109/TPAMI.2005.227 Copyright Statement Copyright 2005 IEEE. Personal use of this material is permitted. However, permission to reprint/ republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Downloaded from /10072/4262 Link to published version /xpls/abs_all.jsp?isnumber=32376arnumber=1512053count=14index=3 1720 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 11, NOVEMBER 2005 Texture for Script Identification Andrew Busch, Member, IEEE, Wageeh W. Boles, Member, IEEE, and Sridha Sridharan, Senior Member, IEEE Abstract—The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed. Index Terms—Script identif