Abstract—This paper presents the recognition of off line handwritten English characters using the forward only Counter Propagation network (CPN) algorithm Upper case English alphabets are used in this paper. In the recognition process different people’s writing style are gathered. The obtained results in this paper show the effect of the learning rate and recognition accuracy of the CPN neural network. The algorithm is tested and the recognition rate obtained was over 90%.It shows that proposed algorithm results are reasonable and acceptable for the hand written character recognition application.
Index Terms—Handwritten character recognition, counter propagation networks, learning rate, performance
W. H. Bangyal, J. Ahmad, and Q. Abbas
[PDF]
Cite: W. H. Bangyal, J. Ahmad, and Q. Abbas, "Recognition of Off-line Isolated Handwritten Character Using Counter Propagation Network," International Journal of Engineering and Technology vol. 5, no. 2, pp. 227-230, 2013.