Research on Human Skin Condition Evaluation based on Neural Network

DOI

10.2991/iccsae-15.2016.120How to use a DOI?

Keywords

neural network; classification; the status of human skin; evaluation.

Abstract

With the continuous development of peoples’ life, the skin-care is attracting more attention. There are so many factors affecting the skin condition, and there is nonlinear correlation between factors. However, the current research always use single index to evaluate skin condition which would not be accurate. This article is to introduce seven key factors which affect the skin conditions into the evaluation. The skin condition classification model is built by the BP neural network according to the skin condition index. Firstly, on the basis of age, the skin condition is classified into three type: youth, middle aged, and the old, then the feature of each kind is extracted, and then according to the seven key factors, the neural network calculation is used to study the skin condition, finally, the neural network classification result is compared with the real age to complete the evaluation. The result proves that, by using the method this article introduced in the classification of skin condition, the similarity with the real age can be 70%, BP neural network can evaluate the skin condition effectively. In addition, the method is simple and practical which supplies effective way to do the evaluation. The physical significance of the evaluation is clear and it uses the difference-information in maximum which is the accurate and effective way to obtain the skin condition information.

Copyright

© 2016, 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  - Chang Liu
AU  - Li Wang
AU  - Xiaoyi Wang
AU  - Jiping Xu
AU  - Huiyan Zhang
AU  - Yinmou Dong
PY  - 2016/02
DA  - 2016/02
TI  - Research on Human Skin Condition Evaluation based on Neural Network
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 641
EP  - 648
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.120
DO  - 10.2991/iccsae-15.2016.120
ID  - Liu2016/02
ER  -