Handwritten Text Recognition Using CNN

Handwritten Text Recognition Using CNN

Author Name : Rishabh Goel, Ajay Kaushik

ABSTRACT

Recognition of handwritten text is one of the most thought-provoking areas of pattern  recognition. It contributes immensely to the advancement of automation process and improves the interface between machine and man in numerous applications. It is useful while dealing with practical problems, signature verification, mailing bank check processing, interpretation of postal address, documentation analysis, document verification and many others.

The goal of this project is to improve the Handwritten Text Recognition (HTR) System that was developed during the minor project and to make it moreaccurate, efficient, and easily accessible. The HTR model will be able to accurately identify both word as well as text-line images with high recognition accuracy after the completion of this project. With the help of internet and Flask, this system will be made accessible to everyone over the internet.

Keywords: Handwritten Text Recognition, Neural Network, CNN, Deep Learning, Flask