Handwritten Devanagri Numeral Character Recognition using SVN and ANN

Handwritten numeral character recognition is one of the most challenging processes. It also have diverse applicable environment. This paper proposed a system for recognizing offline Handwritten Devanagari numeral character recognition using Support Vector Machine and Artificial Neural Network, both techniques are used as classifier and results are compared. We apply various techniques for image enhancement which are useful to improve the accuracy of the recognition of numeral character such as binarization, noise removable and normalization. Extracting the feature of numeral character we have used statistical and structured based feature of numeral character. We have used Chain Code, Zone Based Centroid, Background Directional Distribution and Distance Profile features feature extraction techniques. We also discussed the segmentation process used in this process. Experiment is carried out by varying the image sizes: 30x30, 40x40, and 50x50 using MATLAB on more than 5,000 samples. The overall recognition accuracy is 99.20 % by using SVM and 98.12 by using ANN.