Features extraction method for arabic characters based on pixel orientation technique

Mohamed A. Ali, Kasmiran Bin Jumari, Salina Abdul Samad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a features extraction module for isolated handwritten Arabic characters. The collected core features are based on pixels orientations according to Freeman chain code. The input to this module is Arabic character (in its basic-shapes i.e. without diacritics). The features extractor module, fed with a skeleton of an isolated character basic-shape, yields global and local features. Feature vector of 12 elements are used. Two features are global while the remaining 10 elements are locals. Neural network classifier is used for aggregating the features for classification decision making.

Original languageEnglish
Title of host publicationInternational Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings
PublisherWorld Scientific and Engineering Academy and Society
Pages292-295
Number of pages4
Volume1
ISBN (Print)9608457564
Publication statusPublished - 20 Nov 2006
EventProceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, CIMMACS '06 - Venice
Duration: 20 Nov 200622 Nov 2006

Other

OtherProceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, CIMMACS '06
CityVenice
Period20/11/0622/11/06

Fingerprint

Feature extraction
Classifiers
Decision making
Pixels
Neural networks

Keywords

  • Arabic handwritten recognition
  • Features extraction
  • Optical Character Recognition (OCR)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Cite this

Ali, M. A., Bin Jumari, K., & Abdul Samad, S. (2006). Features extraction method for arabic characters based on pixel orientation technique. In International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings (Vol. 1, pp. 292-295). World Scientific and Engineering Academy and Society.

Features extraction method for arabic characters based on pixel orientation technique. / Ali, Mohamed A.; Bin Jumari, Kasmiran; Abdul Samad, Salina.

International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings. Vol. 1 World Scientific and Engineering Academy and Society, 2006. p. 292-295.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ali, MA, Bin Jumari, K & Abdul Samad, S 2006, Features extraction method for arabic characters based on pixel orientation technique. in International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings. vol. 1, World Scientific and Engineering Academy and Society, pp. 292-295, Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, CIMMACS '06, Venice, 20/11/06.
Ali MA, Bin Jumari K, Abdul Samad S. Features extraction method for arabic characters based on pixel orientation technique. In International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings. Vol. 1. World Scientific and Engineering Academy and Society. 2006. p. 292-295
Ali, Mohamed A. ; Bin Jumari, Kasmiran ; Abdul Samad, Salina. / Features extraction method for arabic characters based on pixel orientation technique. International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings. Vol. 1 World Scientific and Engineering Academy and Society, 2006. pp. 292-295
@inproceedings{0990a1fab3694b7698315cf659dc818e,
title = "Features extraction method for arabic characters based on pixel orientation technique",
abstract = "This paper presents a features extraction module for isolated handwritten Arabic characters. The collected core features are based on pixels orientations according to Freeman chain code. The input to this module is Arabic character (in its basic-shapes i.e. without diacritics). The features extractor module, fed with a skeleton of an isolated character basic-shape, yields global and local features. Feature vector of 12 elements are used. Two features are global while the remaining 10 elements are locals. Neural network classifier is used for aggregating the features for classification decision making.",
keywords = "Arabic handwritten recognition, Features extraction, Optical Character Recognition (OCR)",
author = "Ali, {Mohamed A.} and {Bin Jumari}, Kasmiran and {Abdul Samad}, Salina",
year = "2006",
month = "11",
day = "20",
language = "English",
isbn = "9608457564",
volume = "1",
pages = "292--295",
booktitle = "International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings",
publisher = "World Scientific and Engineering Academy and Society",

}

TY - GEN

T1 - Features extraction method for arabic characters based on pixel orientation technique

AU - Ali, Mohamed A.

AU - Bin Jumari, Kasmiran

AU - Abdul Samad, Salina

PY - 2006/11/20

Y1 - 2006/11/20

N2 - This paper presents a features extraction module for isolated handwritten Arabic characters. The collected core features are based on pixels orientations according to Freeman chain code. The input to this module is Arabic character (in its basic-shapes i.e. without diacritics). The features extractor module, fed with a skeleton of an isolated character basic-shape, yields global and local features. Feature vector of 12 elements are used. Two features are global while the remaining 10 elements are locals. Neural network classifier is used for aggregating the features for classification decision making.

AB - This paper presents a features extraction module for isolated handwritten Arabic characters. The collected core features are based on pixels orientations according to Freeman chain code. The input to this module is Arabic character (in its basic-shapes i.e. without diacritics). The features extractor module, fed with a skeleton of an isolated character basic-shape, yields global and local features. Feature vector of 12 elements are used. Two features are global while the remaining 10 elements are locals. Neural network classifier is used for aggregating the features for classification decision making.

KW - Arabic handwritten recognition

KW - Features extraction

KW - Optical Character Recognition (OCR)

UR - http://www.scopus.com/inward/record.url?scp=84905737340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905737340&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9608457564

VL - 1

SP - 292

EP - 295

BT - International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings

PB - World Scientific and Engineering Academy and Society

ER -