Journal
MULTIMEDIA TOOLS AND APPLICATIONS
Volume 76, Issue 21, Pages 22043-22058Publisher
SPRINGER
DOI: 10.1007/s11042-017-4782-y
Keywords
Pose-and-illumination-invariant feature; Face reconstruction neural network; Triplet-loss training
Categories
Funding
- National Key Research and Development Program of China [2016YFB1000903]
- NSFC [61573268]
Ask authors/readers for more resources
Face recognition under variable pose and illumination is a challenging problem in computer vision tasks. In this paper, we solve this problem by proposing a new residual based deep face reconstruction neural network to extract discriminative pose-and-illumination-invariant (PII) features. Our deep model can change arbitrary pose and illumination face images to the frontal view with standard illumination. We propose a new triplet-loss training method instead of Euclidean loss to optimize our model, which has two advantages: a) The training triplets can be easily augmented by freely choosing combinations of labeled face images, in this way, overfitting can be avoided; b) The triplet-loss training makes the PII features more discriminative even when training samples have similar appearance. By using our PII features, we achieve 83.8% average recognition accuracy on MultiPIE face dataset which is competitive to the state-of-the-art face recognition methods.
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