Age Estimation Based on a Deep Model

DOI

10.2991/eame-18.2018.64How to use a DOI?

Keywords

deep convolutional neural networks; fine-tune; face age estimation; maximum joint probability classifierstyling

Abstract

In this paper, we propose a new age classification method based on a deep model. In our method, the fine-tuned deep facial age (FTDFA) model is used to extract facial age features. Age features output from the activations of the penultimate layer are classified by the Maximum joint probability classifier(MJPCCR).Three data sets are used to validate our approach. And we also send the age features output from the activations of the last layer into the MJPC and the SVM classifier separately, and compare their results. Experiments show that, the performance of our method is superior to that of the previous methods.

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  - Liming Chen
PY  - 2018/06
DA  - 2018/06
TI  - Age Estimation Based on a Deep Model
BT  - Proceedings of the 2018 3rd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2018)
PB  - Atlantis Press
SP  - 304
EP  - 307
SN  - 2352-5401
UR  - https://doi.org/10.2991/eame-18.2018.64
DO  - 10.2991/eame-18.2018.64
ID  - Chen2018/06
ER  -