Study on Image Recognition Based on Stacked Sparse Auto-encoder

DOI

10.2991/eeeis-17.2017.52How to use a DOI?

Keywords

Image Recognition, Sparse Auto-encoder, Feature Extraction.

Abstract

Image recognition has the characteristics of large sample size, high complexity and redundant information, which has become a hot and difficult topic in the present study. To solve this problem, a feature extraction and image classification model based on the sparse auto-encoder deep neural network is proposed. By using the Greedy layer-wise training, the internal features of the data are learned from the unlabeled data, and the features of the learning are taken as inputs to the softmax classifier. Then, the sparse auto-encoder is tuned by the back propagation algorithm using the data of the label. Finally,the whole model was tested using the test sets data, and compared with the traditional PCA , BP neural network and auto-encoder deep neural network. And the accuracy could reach 91%, which is better than the other methods in the experiment. It has certain practical value for image recognition.

Copyright

© 2017, 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  - Gui-Ming CAO
AU  - Xiang -Qian DING
AU  - Hui -Li GONG
PY  - 2017/09
DA  - 2017/09
TI  - Study on Image Recognition Based on Stacked Sparse Auto-encoder
BT  - Proceedings of the 3rd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2017)
PB  - Atlantis Press
SP  - 372
EP  - 378
SN  - 2352-5401
UR  - https://doi.org/10.2991/eeeis-17.2017.52
DO  - 10.2991/eeeis-17.2017.52
ID  - CAO2017/09
ER  -