DocumentCode
1583057
Title
A framework of combining numeric string recognizers
Author
Ye, Xiangyun ; Cheriet, Mohamed ; Suen, Ching Y.
Author_Institution
Centre for Pattern Recognition & Machine Intelligence, Concordia Univ., Montreal, Que., Canada
fYear
2001
fDate
6/23/1905 12:00:00 AM
Firstpage
716
Lastpage
720
Abstract
Although promising results on the combination of character recognizers have been reported recently, the combination strategies can not be readily applied to the recognition of character strings due to m-n correspondence problems caused by segmentation errors. In this paper, we propose a new paradigm of combining multiple string recognizers and contribute a generic framework for off-line combination. We designed and implemented a graph based off-line combination system, StrCombo, which has achieved a substantial improvement over any one of the individual recognizers in a real-life application. This open combination system provides the possibility of further improving the performance of string recognizers when new recognizers and combination rules are available
Keywords
character recognition; image segmentation; string matching; StrCombo; character recognizers m-n correspondence problems; generic framework; multiple string recognizers; numeric string recognizers; off-line combination; segmentation errors; Artificial intelligence; Character recognition; Handwriting recognition; Image recognition; Laboratories; Machine intelligence; Merging; Optical character recognition software; Pattern recognition; Voting;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location
Seattle, WA
Print_ISBN
0-7695-1263-1
Type
conf
DOI
10.1109/ICDAR.2001.953883
Filename
953883
Link To Document