Face age estimation network based on improved residual blocks

Jia Li Li; Xing Guo Jiang; Cheng Qun Yi; Li He; De Cai Li

doi:10.1117/12.2656973

20 October 2022 Face age estimation network based on improved residual blocks

Jia Li Li, Xing Guo Jiang, Cheng Qun Yi, Li He, De Cai Li

Proceedings Volume 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022); 124514D (2022) https://doi.org/10.1117/12.2656973
Event: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 2022, Chongqing, China

Abstract

To address the problem that age estimation accuracy is affected by face occlusion, uneven illumination, complex expressions and different postures under unconstrained conditions. In this paper, a new network model is constructed based on the pytorch framework and named as RFA network. The RFA network is implemented based on ResNet residual blocks.To reduces network over-fitting by introducing Dropout technique, and uses four improved residual blocks to extract more detailed age features of human faces. The maximum pooling and average pooling are also combined to overcome the problem of feature information loss during feature extraction, so that it can capture more subtle facial features to improve the classification accuracy. After the RFA network is trained and tested, the experimental results show that the average absolute error value of age has reached 3.95, which is lower than the classical networks such as VGG. The effectiveness of RFA algorithm is proved.

Citation Download Citation

Jia Li Li, Xing Guo Jiang, Cheng Qun Yi, Li He, and De Cai Li "Face age estimation network based on improved residual blocks", Proc. SPIE 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 124514D (20 October 2022); https://doi.org/10.1117/12.2656973

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Radiofrequency ablation

Error analysis

Feature extraction

Convolutional neural networks

Image classification

Image analysis

Lithium

Show All Keywords

Keywords/Phrases

Search In:

Publication Years