Issue |
MATEC Web Conf.
Volume 232, 2018
2018 2nd International Conference on Electronic Information Technology and Computer Engineering (EITCE 2018)
|
|
---|---|---|
Article Number | 02021 | |
Number of page(s) | 4 | |
Section | 3D Images Reconstruction and Virtual System | |
DOI | https://doi.org/10.1051/matecconf/201823202021 | |
Published online | 19 November 2018 |
Facial Age Estimation Method Based on Fusion Classification and Regression Model
1
Science and Technology College of Gannan Normal University, GanZhou, JiangXi, China 341000
2
School of Electrical Engineering and Automation, JiangXi University of Science and Technology, GanZhou, JiangXi, China 341000
Due to the large individual differences in the facial features of each person and the fact that the age has a certain time sequence, the age estimation based on face images faces certain difficulties. This article proposes a method based on fusion classification and regression model: A classification model and a regression model are added to the convolutional neural network to train the network under the premise of sharing convolutional layer parameters. The classification of the age of the label is used to code the age distribution, and the age is regressed using the Euclidean distance. The final predicted value of the model is the average of the two. Experiments show that the effect of fusion classification and regression model is better than that of a single model, which improves the accuracy of age estimation.
© The Authors, published by EDP Sciences, 2018
This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.