Affiliation:
1. School of Information Science and Technology, North China University of Technology, Beijing 100144, China
2. Baidu Inc., Beijing 100085, China
3. University of Science and Technology Beijing, Beijing 100083, China
Abstract
Face aging is of great importance for the information forensics and security fields, as well as entertainment-related applications. Although significant progress has been made in this field, the authenticity, age specificity, and identity preservation of generated face images still need further discussion. To better address these issues, a Feature-Guide Conditional Generative Adversarial Network (FG-CGAN) is proposed in this paper, which contains extra feature guide module and age classifier module. To preserve the identity of the input facial image during the generating procedure, in the feature guide module, perceptual loss is introduced to minimize the identity difference between the input and output face image of the generator, and L2 loss is introduced to constrain the size of the generated feature map. To make the generated image fall into the target age group, in the age classifier module, an age-estimated loss is constructed, during which L-Softmax loss is combined to make the sample boundaries of different categories more obvious. Abundant experiments are conducted on the widely used face aging dataset CACD and Morph. The results show that target aging face images generated by FG-CGAN have promising validation confidence for identity preservation. Specifically, the validation confidence levels for age groups 20–30, 30–40, and 40–50 are 95.79%, 95.42%, and 90.77% respectively, which verify the effectiveness of our proposed method.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference40 articles.
1. Tazoe, Y., Gohara, H., Maejima, A., and Morishima, S. (2012). ACM SIGGRAPH 2012 Posters, Association for Computing Machinery.
2. Kemelmacher-Shlizerman, I., Suwajanakorn, S., and Seitz, S.M. (2014, January 23–28). Illumination-aware age progression. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.
3. Toward automatic simulation of aging effects on face images;Lanitis;IEEE Trans. Pattern Anal. Mach. Intell.,2002
4. A compositional and dynamic model for face aging;Suo;IEEE Trans. Pattern Anal. Mach. Intell.,2009
5. A concatenational graph evolution aging model;Suo;IEEE Trans. Pattern Anal. Mach. Intell.,2012