A Novel Lexicon Reduction Method for Arabic Handwriting Recognition

Author

Wshah, Safwan ; Govindaraju, Venu ; Cheng, Yanfen ; Li, Huiping

Author_Institution

Dept. of Comput. Sci. & Eng., Univ. at Buffalo, Amherst, NY, USA

fYear

2010

fDate

23-26 Aug. 2010

Firstpage

2865

Lastpage

2868

Abstract

In this paper, we present a method for lexicon size reduction which can be used as an important pre-processing for an off-line Arabic word recognition. The method involves extraction of the dot descriptors and PAWs (Piece of Arabic Word ). Then the number and position of dots and the number of the PAWs are used to eliminate unlikely candidates. The extraction of the dot descriptors is based on defined rules followed by a convolutional neural network for verification. The reduction algorithm makes use of the combination of two features with a dynamic matching scheme. On IFN/ENIT database of 26459 Arabic handwritten word images we achieved a reduction rate of 87% with accuracy above 93%.

Keywords

convolution; handwriting recognition; natural languages; neural nets; word processing; Arabic handwriting recognition; Arabic handwritten word images; Arabic word piece; IFN-ENIT database; convolutional neural network; dot descriptor extraction; dynamic matching scheme; lexicon reduction method; lexicon size reduction; offline Arabic word recognition; Accuracy; Artificial neural networks; Feature extraction; Handwriting recognition; Image color analysis; Shape; Lexicon redeuction; arabic offline handwritten; handwritten recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2010 20th International Conference on

Conference_Location

Istanbul

ISSN

1051-4651

Print_ISBN

978-1-4244-7542-1

Type

conf

DOI

10.1109/ICPR.2010.702

Filename

5597042