Hand Witten Text Recognition using Deep Learning

Abstract

Abstract: The dependence on people over technology has never been higher, to the point where deep learning and machine learning algorithms can conduct anything from object detection in images to adding sound to silent movies. Similarly, handwritten text recognition is a major field of research and development with a plethora of possibilities. Using this method, the system is taught to look for similarities as well as differences between diverse handwriting samples. This program turns a picture of a handwritten transcription into digital text. Convolution Neural Network (CNN) with the help of IAM databases are used on the proposed work to recognize the handwritten text. Our main goal is to integrate the aforementioned models, with their release times, in order to create the best text recognition possible, model. Keywords: Handwritten Text Recognition (HTR), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Connectionist Temporal Classification (CTC)