Year: 2018
Type: article
Abstract: Deep learning has provided solution to many pattern recognition problems. Convolutional neural network architecture based on deep learning is proposed in this work for handwritten character recognition. The learning of Convolutional neural network (CNN) is called End-to-End learning. This paper highlights the differences between end-to-end learning and traditional learning. A CNN architecture giving an accuracy of 86.7% for Hindi handwritten characters is proposed.
Author: Madhuri Yadav
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W2804734885
