Handwritten Tamil Character Recognition using Convolutional Neural Network


R. Sarala
Pondicherry Engineering College, Puducherry, India
Pondicherry Engineering College, Puducherry, India


Character Recognition in handwritten images is one of the challenging issues in machine vision for document analytics. Handwritten character recognition systems can greatly contribute to the advancement of the automation process and can improve the interaction between man and machine in many applications. Low quality of print and paper and unfamiliar font faces are the most known problems. In the existing system optical character recognition technique is used for analyzing the text. Optical character recognition is not efficient in recognizing the handwritten text and the fonts which are quite similar to handwriting. In such cases machine learning techniques play a better role than Optical character recognition. This paper aims to implement an approach that recognizes the characters in Indian scripts by applying image processing techniques specifically deep learning technique using Convolutional Neural Networks. The convolutional neural Network has been used for the classification of Tamil characters was found to be 98% of accuracy.

ICICCAS20 Cover Page
July 29, 2020