SVM based off-line handwritten digit recognition

Selection of classifiers plays a very important role in achieving best possible accuracy of classification. In this proposed work an efficient Support Vector Machine based off-line handwritten character recognition system has been developed. Experiments have been performed using well known standard database acquired from CEDAR, also we propose four different techniques of feature extraction to construct the final feature vector. Experimental results show that the performance of SVM is much better than other techniques reported in literature.