?In this project,?describes the classification of Tamil character recognition using Deep learning.We classify characters inTamil,a south Indian language, using convolutional neuralnetworks(ConvNets) into different classes.
ConvNets are biologically inspired neural networks .Humans can easily recognize handwritten words, after gaining basic knowledge of languages. This knowledge needs to be transferred to computers for automatic character recognition.
The work proposed in this paper tries to automate recognition of hindi isolated characters using CNN. For feature extraction, it uses histogram of oriented gradients as one feature and profile projection histogram as another feature.
The performance of various classifiers has been evaluated using confusion matrix ,specificity,sensitivity and accuracy.