An efficient scheme for tilt correction in Arabic OCR system

M. Sarfraz; S. A. Shahab

doi:10.1109/CGIV.2005.17

An efficient scheme for tilt correction in Arabic OCR system

M. Sarfraz^*, S. A. Shahab

^*Corresponding author for this work

King Fahd University of Petroleum & Minerals

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Preprocessing stage is required in almost every image processing application ranging from biometric analysis to document image analysis. An input image or information need to be normalized and converted into format acceptable by OCR (Optical Character Recognition) system. OCR systems typically assume that documents were printed with a single direction of the text and that the acquisition process did not introduce a relevant skew. Practically this assumption is not very strong and printed documents could be skewed at some angle with horizontal axis. In this paper, we have proposed skew estimation of document images for Arabic fonts. It is based upon the specific feature of Arabic script. In our proposed scheme, we scan for the occurrence of letter 'alif 'and estimate the tilt based upon its slope. Extensive experimentation was performed and scheme was found to be very effective.

Original language	English
Title of host publication	Proceedings of the Conference on Computer Graphics, Imaging and Vision
Subtitle of host publication	New Trends 2005
Pages	379-384
Number of pages	6
DOIs	https://doi.org/10.1109/CGIV.2005.17
State	Published - 2005

Publication series

Name	Proceedings of the Conference on Computer Graphics, Imaging and Vision: New Trends 2005
Volume	2005

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/CGIV.2005.17

Cite this

@inproceedings{9135795b55744ec1880150540b7d20ed,

title = "An efficient scheme for tilt correction in Arabic OCR system",

abstract = "Preprocessing stage is required in almost every image processing application ranging from biometric analysis to document image analysis. An input image or information need to be normalized and converted into format acceptable by OCR (Optical Character Recognition) system. OCR systems typically assume that documents were printed with a single direction of the text and that the acquisition process did not introduce a relevant skew. Practically this assumption is not very strong and printed documents could be skewed at some angle with horizontal axis. In this paper, we have proposed skew estimation of document images for Arabic fonts. It is based upon the specific feature of Arabic script. In our proposed scheme, we scan for the occurrence of letter 'alif 'and estimate the tilt based upon its slope. Extensive experimentation was performed and scheme was found to be very effective.",

author = "M. Sarfraz and Shahab, \{S. A.\}",

year = "2005",

doi = "10.1109/CGIV.2005.17",

language = "English",

isbn = "0769523927",

series = "Proceedings of the Conference on Computer Graphics, Imaging and Vision: New Trends 2005",

pages = "379--384",

booktitle = "Proceedings of the Conference on Computer Graphics, Imaging and Vision",

}

An efficient scheme for tilt correction in Arabic OCR system. / Sarfraz, M.; Shahab, S. A.
Proceedings of the Conference on Computer Graphics, Imaging and Vision: New Trends 2005. 2005. p. 379-384 1521091 (Proceedings of the Conference on Computer Graphics, Imaging and Vision: New Trends 2005; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An efficient scheme for tilt correction in Arabic OCR system

AU - Sarfraz, M.

AU - Shahab, S. A.

PY - 2005

Y1 - 2005

N2 - Preprocessing stage is required in almost every image processing application ranging from biometric analysis to document image analysis. An input image or information need to be normalized and converted into format acceptable by OCR (Optical Character Recognition) system. OCR systems typically assume that documents were printed with a single direction of the text and that the acquisition process did not introduce a relevant skew. Practically this assumption is not very strong and printed documents could be skewed at some angle with horizontal axis. In this paper, we have proposed skew estimation of document images for Arabic fonts. It is based upon the specific feature of Arabic script. In our proposed scheme, we scan for the occurrence of letter 'alif 'and estimate the tilt based upon its slope. Extensive experimentation was performed and scheme was found to be very effective.

AB - Preprocessing stage is required in almost every image processing application ranging from biometric analysis to document image analysis. An input image or information need to be normalized and converted into format acceptable by OCR (Optical Character Recognition) system. OCR systems typically assume that documents were printed with a single direction of the text and that the acquisition process did not introduce a relevant skew. Practically this assumption is not very strong and printed documents could be skewed at some angle with horizontal axis. In this paper, we have proposed skew estimation of document images for Arabic fonts. It is based upon the specific feature of Arabic script. In our proposed scheme, we scan for the occurrence of letter 'alif 'and estimate the tilt based upon its slope. Extensive experimentation was performed and scheme was found to be very effective.

UR - https://www.scopus.com/pages/publications/33748852250

U2 - 10.1109/CGIV.2005.17

DO - 10.1109/CGIV.2005.17

M3 - Conference contribution

AN - SCOPUS:33748852250

SN - 0769523927

SN - 9780769523927

T3 - Proceedings of the Conference on Computer Graphics, Imaging and Vision: New Trends 2005

SP - 379

EP - 384

BT - Proceedings of the Conference on Computer Graphics, Imaging and Vision

ER -

An efficient scheme for tilt correction in Arabic OCR system

Abstract

Publication series

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this