High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Contribution Towards Improving Handwriting Text Recognition System

Author(s):

Pranav Thakur , Government Polytechnic College, Betul, Madhya Pradesh, India; Ritesh Pandey, Government Polytechnic College, Betul, Madhya Pradesh, India

Keywords:

Handwriting Text Recognition (HTR), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN)

Abstract

In this research, we present a novel handwriting text recognition (HTR) system developed as part of our major project. The system integrates Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) to accurately recognize and process handwritten text. The primary dataset utilized is the IAM dataset, renowned for its comprehensive coverage and high variability in handwritten styles. This paper discusses the challenges encountered during the development process, including dataset selection and neural network design. Our motivation stems from the significant demand for HTR systems in various sectors, exemplified by the Indian "Regional Transport Office" which employs similar technology for traffic rule enforcement. We aim to advance the field of HTR by addressing existing problems and proposing innovative solutions.

Other Details

Paper ID: IJSRDV12I40065
Published in: Volume : 12, Issue : 4
Publication Date: 01/07/2024
Page(s): 60-63

Article Preview

Download Article