Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.13/44962

OpenURL Link
Title
An effective character extraction algorithm for optical character recognition
Author/Creator
Luo, Suhuai;  Park, Mira;  Hu, Qingmao
Institution
The University of Newcastle. Faculty of Science & Information Technology, School of Design, Communication and Information Technology
Description
This paper introduces an effective character extraction algorithm that can be used for optical character recognition (OCR). Using both geometrical and colour information, the character extraction algorithm can extract text from colour document images which contain mixed text and pictures. The algorithm consists of three components, i.e., adaptive k-means clustering, binary morphological processing, and shape and space-related refinement. When the algorithm is used as a plug-in pre-processing stage for an OCR system, the performance of the system can be improved. Character recognition experiment was done with a commercial OCR package. It has been shown that our algorithm can improve character recognition rate on complex document from 73.1% to 95.5% on average.
Relation
Asia-Pacific Workshop Visual Information Processing. Proceeding for the Asia-Pacific Workshop Visual Information Processing (Beijing, China 7-9th November, 2006) p. 219-223
Relation
http://www.nlpr.ia.ac.cn/VIP2006
Date
2006
Publisher
NLPR
Keyword(s)
optical character recognition (OCR);  character extraction;  text extraction
Resource Type
conference paper
Identifier
http://hdl.handle.net/1959.13/44962
Identifier
ISBN:192070180X
Reviewed
Reviewed
20 Visitors 32 Hits 1 Downloads
Save/E-mail Citation
Citation Format
E-mail Address
Subject
"An effective character extraction algorithm for optical character recognition"
 
OR