The Recognition and Implementation of Handwritten Character based on Deep Learning

Authors
Fengzhi Dai1, *, Zhongyong Ye1, Xia Jin1, 2
1Department of Automation, College of Electronic Information and Automation, Tianjin University of Science and Technology, China
2Tianjin Tianke Intelligent and Manufacture Technology Co., Ltd., China
*Corresponding author. Email: [email protected]
Corresponding Author
Fengzhi Dai
Received 23 October 2018, Accepted 20 November 2018, Available Online 25 June 2019.
DOI
https://doi.org/10.2991/jrnal.k.190601.002How to use a DOI?
Keywords
Deep learning; machine learning; pattern recognition; handwritten character recognition; convolution neural network
Abstract
This paper mainly focuses on the recognition of Chinese handwritten characters. By using the deep learning technology, a deep convolution neural network (CNN) is constructed to identify the handwritten character set, and finally gets the network structure that can be used for recognition. By comparing with other handwritten characters, the engineering application value of the network structure used in this paper is proved, and finally the handwritten character recognition system based on this model also embodies the feasibility of the network structure.
Copyright
© 2019 The Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).