DocumentCode
2022137
Title
A Multi-stream Approach to Off-Line Handwritten Word Recognition
Author
Kessentini, Yousri ; Paquet, Thiery ; Benhamadou, AbdelMajid
Author_Institution
Univ. of Rouen, Rouen
Volume
1
fYear
2007
fDate
23-26 Sept. 2007
Firstpage
317
Lastpage
321
Abstract
We present in this paper a new approach based on multi-stream hidden Markov models (HMM) for the recognition of off-line handwriting. Every word is presented by two HMM models: the first one is learned with features extracted from upper contour, the second with features extracted from lower contour. The combination of these two sources of information is studied using the multi-stream framework. We present experiment results obtained on a database composed of isolated words extracted from incoming mail documents.
Keywords
handwriting recognition; hidden Markov models; word processing; incoming mail documents; isolated words; multistream hidden Markov models; offline handwritten word recognition; Handwriting recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location
Parana
ISSN
1520-5363
Print_ISBN
978-0-7695-2822-9
Type
conf
DOI
10.1109/ICDAR.2007.4378724
Filename
4378724
Link To Document