Multi-font Script Identification Using Texture

There are no files associated with this record.

Title Multi-font Script Identification Using Texture
Author Busch, Andrew William
Publication Title Proceedings of Microelectronic Research Conference 2005
Year Published 2006
Place of publication Nathan, QLD, Australia
Publisher School of Microelectronic Engineering, Griffith University
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, for example as a precursor to OCR. Previous work has shown that visual texture is an effective method of performing script recognition, however such an approach is highly susceptible to changes in font. In this paper, a method of multi-font script recognition using a clustered discriminate function is proposed, allowing the training of a single model for each script class incorporating all fonts. Experimental evidence shows that such an approach can lead to significantly reduced error rates when classifying multi-font scripts.
Peer Reviewed No
Published Yes
Conference name Microelectronic Research Conference, 2005
Location Brisbane, QLD, Australia
Date From 2005-11-02
Date To 2005-11-03
Date Accessioned 2006-07-10
Language en_AU
Faculty Faculty of Engineering and Information Technology
Subject Image Processing
Publication Type Conference Publications (Full Written Paper - Non-Refereed)
Publication Type Code e2

Show simple item record

Griffith University copyright notice