Paper Info
Title
Knowledge-Based Baseline Detection and Optimal Thresholding for Words Segmentation in Efficient Pre-Processing of Handwritten Arabic Text
Abstract
Techniques on detecting baseline and segmenting words in handwritten Arabic text are presented in this paper. Instead of using pure projection, knowledge of the location of the baseline is utilized for accurate baseline detection. Then, distances between words and subwords are respectively analyzed, and their statistical distributions are obtained to decide an optimal threshold in segmenting words. Results on IFN/ENIT database have validated our methods in terms of improved baseline detection and words segmentation for further recognition.
Year
DOI
Venue
2008
10.1109/ITNG.2008.71
Las Vegas, NV
Keywords
Field
DocType
former version,extensible web service-based framework,current ogsa-dai release,words segmentation,handwritten arabic text,knowledge-based baseline detection,data resource,ogsa-dai gt,optimal thresholding,efficient pre-processing,grid fabric,natural language processing,pixel,knowledge based systems,word segmentation,image segmentation,information technology,segmentation,statistical distribution,text analysis,informatics,baseline,handwriting recognition,statistical distributions,knowledge base
Text mining,Pattern recognition,Segmentation,Computer science,Knowledge-based systems,Handwriting recognition,Speech recognition,Image segmentation,Probability distribution,Pixel,Artificial intelligence,Thresholding
Conference
ISBN
Citations 
PageRank 
0-7695-3099-0
10
0.61
References 
Authors
7
4
Name
Order
Citations
PageRank
Jawad H AlKhateeb1452.73
Jinchang Ren2114488.54
Stan S. Ipson3121.68
Jianmin Jiang498581.39