Prediction Of Writer Using Tamil Handwritten Document Image Based On Pooled Features

T. Thendral, M. S. Vijaya, S. Karpagavalli
2015 Zenodo  
Tamil handwritten document is taken as a key source of data to identify the writer. Tamil is a classical language which has 247 characters include compound characters, consonants, vowels and special character. Most characters of Tamil are multifaceted in nature. Handwriting is a unique feature of an individual. Writer may change their handwritings according to their frame of mind and this place a risky challenge in identifying the writer. A new discriminative model with pooled features of
more » ... iting is proposed and implemented using support vector machine. It has been reported on 100% of prediction accuracy by RBF and polynomial kernel based classification model.
doi:10.5281/zenodo.1108868 fatcat:2ws55hhuhrbm5awlfd267ndruy