Classification of Handwritten Ancient Tamil characters using Complex Extreme Learning Machine

1 Research Scholar, 2 Professor Department of Computer Science Avinashilingam University for Women, Coimbatore, Tamil Nadu, India. _____________________________________________________________________________________ Abstract: Classification is the problem of identifying, to which set of categories a new observation belongs, on the basis of a training set whose category membership is known. The process of handwritten script classification involves extraction of some defined characteristics called features to classify an unknown handwritten character into one of the known classes. Zernike moments and regional features are extracted from the Tamil characters and they are formed as feature vectors. Complex Extreme Learning Machine is used to classify the handwritten ancient Tamil characters. Complex Extreme Learning Machine is trained with feature vectors. From the experimental result it is observed that the classifier when trained by combining Zernike moments with regional features gives a highest classification accuracy of 82.63%.