Recognition of Isolated Handwritten Latin Characters using One Continuous Route of Freeman Chain Code Representation and Feedforward Neural Network Classifier
In a handwriting recognition problem, characters can
be represented using chain codes. The main problem in representing
characters using chain code is optimizing the length of the chain
code. This paper proposes to use randomized algorithm to minimize
the length of Freeman Chain Codes (FCC) generated from isolated
handwritten characters. Feedforward neural network is used in the
classification stage to recognize the image characters. Our test results
show that by applying the proposed model, we reached a relatively
high accuracy for the problem of isolated handwritten when tested on
NIST database.
[1] Tay, Y.H., Offline Handwriting Recognition using Artificial Neural
Network and Hidden Markov Model. PhD Thesis. Universiti Teknologi
Malaysia, 2002.
[2] Al-Rashaideh, H., Preprocessing Phase for Arabic Word Handwritten
Recognition. Information Transmission in Computer Network. 2006.
[3] Steinherz, T., Rivlin, E., Intrator, N., Off-Line Cursive Script Word
Recognition - A Survey. International Journal on Document Analysis and
Recognition. 1999.
[4] Mingqiang, Y., Kidiyo, K., Joseph, R., A Survey of Shape Feature
Extraction Techniques. Book Pattern Recognition (Edited by: Peng-
Yeng Yin). November 2008. IN-TECH.
[5] Wegener, I., Towards a Theory of Randomized Search Heuristics.
Lecturer Notes in Computer Science. Springer. 2003.
[6] Ravichandran, A., An Algorithm for Thinning Noisy Images.
International Conference on Acoustics Speech and Signal Processing,
1990.
[7] Alba, E., Chicana, J.F., Training Neural network with GA Hybrid
Algorithm. Proc of GECCO-04. Seattle, Washington. 2004.
[8] Chen, T-P, Tian.J-X., The Research of Artificial Neural Network as a
Tool of Adjustment Prediction in Eco-City Construction. Proceedings of
the Fourth International Conference on Machine Learning and
Cybernetics, Guangzhou, 18-21 August 2005.
[1] Tay, Y.H., Offline Handwriting Recognition using Artificial Neural
Network and Hidden Markov Model. PhD Thesis. Universiti Teknologi
Malaysia, 2002.
[2] Al-Rashaideh, H., Preprocessing Phase for Arabic Word Handwritten
Recognition. Information Transmission in Computer Network. 2006.
[3] Steinherz, T., Rivlin, E., Intrator, N., Off-Line Cursive Script Word
Recognition - A Survey. International Journal on Document Analysis and
Recognition. 1999.
[4] Mingqiang, Y., Kidiyo, K., Joseph, R., A Survey of Shape Feature
Extraction Techniques. Book Pattern Recognition (Edited by: Peng-
Yeng Yin). November 2008. IN-TECH.
[5] Wegener, I., Towards a Theory of Randomized Search Heuristics.
Lecturer Notes in Computer Science. Springer. 2003.
[6] Ravichandran, A., An Algorithm for Thinning Noisy Images.
International Conference on Acoustics Speech and Signal Processing,
1990.
[7] Alba, E., Chicana, J.F., Training Neural network with GA Hybrid
Algorithm. Proc of GECCO-04. Seattle, Washington. 2004.
[8] Chen, T-P, Tian.J-X., The Research of Artificial Neural Network as a
Tool of Adjustment Prediction in Eco-City Construction. Proceedings of
the Fourth International Conference on Machine Learning and
Cybernetics, Guangzhou, 18-21 August 2005.
@article{"International Journal of Information, Control and Computer Sciences:57959", author = "Dewi Nasien and Siti S. Yuhaniz and Habibollah Haron", title = "Recognition of Isolated Handwritten Latin Characters using One Continuous Route of Freeman Chain Code Representation and Feedforward Neural Network Classifier", abstract = "In a handwriting recognition problem, characters can
be represented using chain codes. The main problem in representing
characters using chain code is optimizing the length of the chain
code. This paper proposes to use randomized algorithm to minimize
the length of Freeman Chain Codes (FCC) generated from isolated
handwritten characters. Feedforward neural network is used in the
classification stage to recognize the image characters. Our test results
show that by applying the proposed model, we reached a relatively
high accuracy for the problem of isolated handwritten when tested on
NIST database.", keywords = "Handwriting Recognition, Freeman Chain Code andFeedforward Backpropagation Neural Networks.", volume = "4", number = "7", pages = "1168-7", }