Abstract

AN IN-DEPTH ANALYSIS OF NEURAL NETWORK APPLICATION FOR HAND-WRITTEN CHARACTER RECOGNITION

Vineet Sehrawat

74-80

Vol: 8, Issue: 4, 2018

Different writing styles are remarkable, making it trying to distinguish characters that were composed manually. Transcribed character acknowledgment has turned into the subject of investigation in the most recent couple of a long time through an examination of brain organizations. Dialects composed from left to right, like Hindi, are perused from beginning to end plan. To perceive these kinds of composition, we present a Deep Learning-based manually written Hindi person acknowledgment framework using profound learning procedures like Convolutional Neural Networks (CNN) with Optimizer Adaptive Moment Estimation (Adam) and Deep Neural Networks (DNN) in this paper. The proposed framework was prepared on examples from numerous information base pictures and afterward assessed on images from a client characterized informational index, resulting in very high precision rates.

Download PDF
Back

Disclaimer: All papers published in IJRST will be indexed on Google Search Engine as per their policy.