Paper Info
Title
Lexicon Reduction Using Segment Descriptors for Arabic Handwriting Recognition
Abstract
This paper presents a robust lexicon reduction technique using segment descriptors for Arabic handwritten text. The method segments an Arabic word into graphemes and adaptively generates a descriptor of the presence/absence of dots in those segments. The segmentation algorithm is based on the characteristic of Arabic script, which indicates predictable segmentations of Arabic characters. This in turn results in novel canonical segment descriptors for the lexicon entries. These descriptors are then used for lexicon reduction using a matching algorithm adapted for Arabic handwriting. Unlike other methods, features based on segment descriptors are computable for both word images and lexicon entries. Experimental results are reported on IfN/ENIT database which compare favorably with other approaches for lexicon reduction.
Year
DOI
Venue
2013
10.1109/ICDAR.2013.256
Document Analysis and Recognition
Keywords
Field
DocType
handwriting recognition,image segmentation,natural language processing,text detection,Arabic characters,Arabic handwriting recognition,Arabic script,lexicon entries,matching algorithm,robust lexicon reduction technique,segment descriptors,word images,canonical descriptor,dot assignment,lexicon reduction,segment descriptor
Pattern recognition,Computer science,Arabic handwriting recognition,Segmentation,Handwriting recognition,Image segmentation,Lexicon,Natural language processing,Artificial intelligence,Segment descriptor,Blossom algorithm,Arabic script
Conference
ISSN
Citations 
PageRank 
1520-5363
0
0.34
References 
Authors
7
2
Name
Order
Citations
PageRank
Mohammad Tanvir Parvez11699.19
Sabri A. Mahmoud244333.96