OFFLINE HANDWRITING RECOGNITION USING GENETIC ALGORITHM

Abstract

In this paper, a new method for offline handwriting recognition is presented. A robust algorithm for \nhandwriting segmentation has been described here with the help of which individual characters can be \nsegmented from a word selected from a paragraph of handwritten text image which is given as input to the \nmodule. Then each of the segmented characters are converted into column vectors of 625 values that are later \nfed into the advanced neural network setup that has been designed in the form of text files. The networks has \nbeen designed with quadruple layered neural network with 625 input and 26 output neurons each corresponding \nto a character from a-z, the outputs of all the four networks is fed into the genetic algorithm which has been \ndeveloped using the concepts of correlation, with the help of this the overall network is optimized with the help of \ngenetic algorithm thus providing us with recognized outputs with great efficiency of 71%.