Handwritten Devanagari Character Recognition Using Artificial Neural Network .

Handwritten character recognition in Indian script is a challenging task specially Devanagari, for several reason like complex structure of character with their modifiers and present of compound character. Devanagari character recognition will prove beneficial to 18% of world’s population. Devanagari character recognition is applicable to various application areas where the aim is automation and to reduce the human efforts for form filling, job application, bank cheque processing system and postal automation etc. Devanagari character recognition system can be used as a reading aid to blind and it also has application in forensic science. It can thus contribute immensely to the advancement of automation processes and can improve the interface between man and machine in many applications. Artificial Neural networks have good learning and generalization abilities which are necessary for dealing with imprecision in input patterns and perform satisfactorily in the presence of incomplete or noisy data. Artificial Neural Network is one of the most widely used and popular techniques for character recognition problem. This paper discusses the classification and recognition of handwritten Devanagari character recognition using Artificial Neural Networks in four stages - 1) Scanning, 2) Preprocessing, 3) Feature Extraction and, 4) Recognition. When a test character is given, appropriate neural network is invoked to recognize the character in that group, based on the features in that character. The accuracy of the network is analyzed by giving various test patterns to the system. The average accuracy of recognition of the system is 94.43%.