A method of go recognition based on Deep Learning

DOI

10.2991/mecae-18.2018.45How to use a DOI?

Keywords

Deep learning, go, image processing.

Abstract

In order to obtain the image information of go, we use the traditional method to process the image, but the traditional method has great limitation. The accuracy is low, and the external factors can easily affect the processing result. In order to solve the limitation of traditional image processing method, we will introduce and study a new image processing method-depth learning. First, we prepare a picture sample of go, and then we use two methods to identify the image of go. Finally, the recognition results of the traditional method and the recognition results of the depth learning are compared. The results show that the accuracy of the depth learning method is improved by 17.1% compared with the traditional method.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Heng Ran
AU  - Pengyun Song
AU  - Yanghui Liu
AU  - Lei Yu
AU  - Hang Zhou
AU  - Yinrui Zhang
PY  - 2018/03
DA  - 2018/03
TI  - A method of go recognition based on Deep Learning
BT  - Proceedings of the 2018 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2018)
PB  - Atlantis Press
SN  - 2352-5401
UR  - https://doi.org/10.2991/mecae-18.2018.45
DO  - 10.2991/mecae-18.2018.45
ID  - Ran2018/03
ER  -