DocumentCode
1580401
Title
Probabilistic model for segmentation based word recognition with lexicon
Author
Tulyakov, Sergey ; Govindaraju, Venu
Author_Institution
CEDAR, State Univ. of New York, Buffalo, NY, USA
fYear
2001
fDate
6/23/1905 12:00:00 AM
Firstpage
164
Lastpage
167
Abstract
We describe the construction of a model for off-line word recognizers based on over-segmentation of the input image and recognition of segment combinations as characters in a given lexicon word. One such recognizer, the Word Model Recognizer (WMR), is used extensively. Based on the proposed model it was possible to improve the performance of WMR
Keywords
document image processing; handwritten character recognition; image segmentation; optical character recognition; probability; OCR; Word Model Recognizer; handwritten word recognition; image segmentation; lexicon; offline word recognizers; optical character recognition; performance evaluation; probabilistic model; segmentation based word recognition; Arithmetic; Character recognition; Data mining; Image quality; Image recognition; Image segmentation; Mathematical model; Optical character recognition software; Venus; Writing;
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.2001.953776
Filename
953776
Link To Document