Recognition of Off-Line Handwritten Devanagari Characters Using 64dimensional Feature Extraction

ABSTRACT Recognition of handwritten characters is a challenging task because of the variability involved in the writing styles of different individuals. In this paper we are concern with features from 64 dimensional feature extraction techniques for the Devanagari character. These features are used for further classification. Histograms of direction chain code of the contour points of the characters are used as feature for recognition [4].From this we get 196 features for future classification. We suppose to be used Multi Layer Perceptron (MLP) based Classifier.