Comparison Optimization for Image Classification based on Deep Belief Network

DOI

10.2991/mcei-18.2018.37How to use a DOI?

Keywords

Image classification and identification; Intelligent robotics and control engineering; Deep learning; Image feature extraction

Abstract

In the field of intelligent robotics and control engineering, image classification technology based on deep learning is of great significance for robot image identification and has gained a wider range of applications. However, when it comes to the actual working environment of the robot, the existences of light illumination, noise and other factors will make the result of deep learning frame merely not satisfied. This paper focuses on the comparison of different feature extraction methods for optimization of DBN (Deep Belief Networks). Experimental results show that these methods can improve the accuracy of image classification.

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  - Daohan Yang
AU  - Xiao Yao
AU  - Wensong Bai
AU  - Bin Wang
AU  - Runyu Wang
AU  - Zuxi Zhang
PY  - 2018/06
DA  - 2018/06
TI  - Comparison Optimization for Image Classification based on Deep Belief Network
BT  - Proceedings of the 2018 8th International Conference on Mechatronics, Computer and Education Informationization (MCEI 2018)
PB  - Atlantis Press
SP  - 191
EP  - 197
SN  - 2352-538X
UR  - https://doi.org/10.2991/mcei-18.2018.37
DO  - 10.2991/mcei-18.2018.37
ID  - Yang2018/06
ER  -