Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten arabic text

J. H. AlKhateeb; Jinchang Ren; S. Ipson; J. Jiang

doi:10.1109/ITNG.2008.71

Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten arabic text

J. H. AlKhateeb, Jinchang Ren, S. Ipson, J. Jiang

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

27 Citations (Scopus)

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

Original language	English
Title of host publication	Proceedings of the 5th international conference on information technology
Subtitle of host publication	new generations
Editors	S Latifi
Publisher	IEEE
Pages	1158-1159
Number of pages	2
ISBN (Print)	9780769530994
DOIs	https://doi.org/10.1109/ITNG.2008.71
Publication status	Published - 2008
Event	5th International Conference on Information Technology - New Generations - Las Vegas, United States Duration: 7 Apr 2008 → 9 Apr 2008

Conference

Conference	5th International Conference on Information Technology - New Generations
Country/Territory	United States
City	Las Vegas
Period	7/04/08 → 9/04/08

Keywords

character-recognition

Access to Document

10.1109/ITNG.2008.71

Cite this

@inproceedings{174da47aee9a40e4a3ab566f22487fcc,

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",

keywords = "character-recognition",

author = "AlKhateeb, {J. H.} and Jinchang Ren and S. Ipson and J. Jiang",

year = "2008",

doi = "10.1109/ITNG.2008.71",

language = "English",

isbn = "9780769530994 ",

pages = "1158--1159",

editor = "{Latifi }, {S }",

booktitle = "Proceedings of the 5th international conference on information technology",

publisher = "IEEE",

note = "5th International Conference on Information Technology - New Generations ; Conference date: 07-04-2008 Through 09-04-2008",

}

AlKhateeb, JH, Ren, J, Ipson, S & Jiang , J 2008, Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten arabic text. in S Latifi (ed.), Proceedings of the 5th international conference on information technology: new generations . IEEE, pp. 1158-1159, 5th International Conference on Information Technology - New Generations, Las Vegas, United States, 7/04/08. https://doi.org/10.1109/ITNG.2008.71

Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten arabic text. / AlKhateeb, J. H.; Ren, Jinchang; Ipson, S. et al.
Proceedings of the 5th international conference on information technology: new generations . ed. / S Latifi . IEEE, 2008. p. 1158-1159.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten arabic text

AU - AlKhateeb, J. H.

AU - Ren, Jinchang

AU - Ipson, S.

AU - Jiang , J.

PY - 2008

Y1 - 2008

N2 - 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

AB - 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

KW - character-recognition

U2 - 10.1109/ITNG.2008.71

DO - 10.1109/ITNG.2008.71

M3 - Conference contribution book

SN - 9780769530994

SP - 1158

EP - 1159

BT - Proceedings of the 5th international conference on information technology

A2 - Latifi , S

PB - IEEE

T2 - 5th International Conference on Information Technology - New Generations

Y2 - 7 April 2008 through 9 April 2008

ER -

Knowledge-based baseline detection and optimal thresholding for words segmentation in efficient pre-processing of handwritten arabic text

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this