An Efficient Offline Tamil Handwritten Character Recognition System using Zernike Moments and Diagonal-based features

Offline Tamil Handwritten character recognition system using a combination of Zernike moments and diagonal features of Zones are proposed in this paper. The proposed recognition system yields higher rate of recognition accuracy compared to the systems developed using the conventional feature extractions using horizontal and vertical methods. Since, Zernike moments are known as better descriptors of shape of an image, 32 moment based features and also 69 diagonal features from zones of the character image are considered as feature vector. Thus the feature vectors containing 101 features generated from the dataset is considered as training set. The recognition was performed using the classifiers such as Neural Network (NN), Euclidean Distance and SVM. Finally, NN was proved to produce better recognition accuracy of 93. 8%.