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
fDate :
6/23/1905 12:00:00 AM
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;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953776
