An Idea to Recognition of Handwritten Characters using Genetic Algorithms

Challenges in handwritten characters recognition is due to the variation and distortion of handwritten characters, since different people use different style and way of draw the same shape of the characters. This paper demonstrates the nature of handwritten characters, conversion of handwritten data into electronic data, and the neural network approach to make machine capable of recognizing hand written characters. This motivates the use of Genetic Algorithms for the problem. In order to prove this, we made a pool of images of characters. We converted them to graphs. The graph of every character was intermixed to generate new or unique styles intermediate between the styles of parent character. Character recognition involved the matching of the graph generated from the unknown character image with the graphs generated by mixing.