Journal
NEUROCOMPUTING
Volume 230, Issue -, Pages 184-196Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2016.12.025
Keywords
Face recognition; Data augmentation; Landmark perturbation; Image synthesis; 3D reconstruction
Categories
Funding
- National Natural Science Foundation of China (NSFC) [61472386]
- Strategic Priority Research Program of the Chinese Academy of Sciences [XDA 06040103]
- Chongqing Research Program of Basic Research and Frontier Technology [cstc2016jcyjA0011]
Ask authors/readers for more resources
Recently, Deep Convolution Neural Networks (DCNNs) have shown outstanding performance in face recognition. However, the supervised training process of DCNN requires a large number of labeled samples which are expensive and time consuming to collect. In this paper, we propose five data augmentation methods dedicated to face images, including landmark perturbation and four synthesis methods (hairstyles, glasses, poses, illuminations). The proposed methods effectively enlarge the training dataset, which alleviates the impacts of misalignment, pose variance, illumination changes and partial occlusions, as well as the overfitting during training. The performance of each data augmentation method is tested on the Multi-PIE database. Furthermore, comparison of these methods are conducted on LFW, YTF and IJB-A databases. Experimental results show that our proposed methods can greatly improve the face recognition performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available