A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network

This paper introduces a novel design for handwritten letter recognition by employing a hybrid back-propagation neural network with an enhanced evolutionary algorithm. Feeding the neural network consists of a new approach which is invariant to translation, rotation, and scaling of input letters. Evolutionary algorithm is used for the global search of the search space and the back-propagation algorithm is used for the local search. The results have been computed by implementing this approach for recognizing 26 English capital letters in the handwritings of different people. The computational results show that the neural network reaches very satisfying results with relatively scarce input data and a promising performance improvement in convergence of the hybrid evolutionary back-propagation algorithms is exhibited.

[1]  Edzard S. Gelsema,et al.  Editorial Special issue on genetic algorithms , 1995, Pattern Recognit. Lett..

[2]  B. V. S. Murthy.  Handwriting recognition using supervised neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[3]  Jamshid Shanbehzadeh,et al.  Image retrieval based on shape similarity by edge orientation autocorrelogram , 2003, Pattern Recognit..

[4]  Dan Boneh,et al.  On genetic algorithms , 1995, COLT '95.

[5]  Wei Gao.  New evolutionary neural networks , 2005, Proceedings. 2005 First International Conference on Neural Interface and Control, 2005..

[6]  Manu Pratap Singh,et al.  Handwritten English Vowels Recognition Using Hybrid Evolutionary Feed-forward Neural Network , 2006 .

[7]  Fariborz Mahmoudi,et al.  Visual Hand Tracking Algorithms , 2006, Geometric Modeling and Imaging--New Trends (GMAI'06).

[8]  M.A. Meinagh,et al.  Database Replication with Availability and Consistency Guarantees through Failure-Handling , 2007, 2007 International Multi-Conference on Computing in the Global Information Technology (ICCGI'07).