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 language | English |
---|---|
Title of host publication | International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics - Proceedings |
Publisher | World Scientific and Engineering Academy and Society |
Pages | 292-295 |
Number of pages | 4 |
Volume | 1 |
ISBN (Print) | 9608457564 |
Publication status | Published - 20 Nov 2006 |
Event | Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, CIMMACS '06 - Venice Duration: 20 Nov 2006 → 22 Nov 2006 |
Other
Other | Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics, CIMMACS '06 |
---|---|
City | Venice |
Period | 20/11/06 → 22/11/06 |
Fingerprint
Keywords
- Arabic handwritten recognition
- Features extraction
- Optical Character Recognition (OCR)
ASJC Scopus subject areas
- Artificial Intelligence
- Human-Computer Interaction
- Software
Cite this
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 proceeding › Conference contribution
}
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
AN - SCOPUS:84905737340
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 -