Dataset Augmentation for Pose and Lighting Invariant Face Recognition
This work addresses a domain-specific problem for face recognition systems by incrementally improving robustness to pose and lighting variations.
The paper tackles the problem of face recognition performance degradation under varying pose and lighting by augmenting training datasets with semi-synthetic images generated via a 3D shape estimation and rendering pipeline, resulting in improved quantitative results on the IJB-A identification dataset.
The performance of modern face recognition systems is a function of the dataset on which they are trained. Most datasets are largely biased toward "near-frontal" views with benign lighting conditions, negatively effecting recognition performance on images that do not meet these criteria. The proposed approach demonstrates how a baseline training set can be augmented to increase pose and lighting variability using semi-synthetic images with simulated pose and lighting conditions. The semi-synthetic images are generated using a fast and robust 3-d shape estimation and rendering pipeline which includes the full head and background. Various methods of incorporating the semi-synthetic renderings into the training procedure of a state of the art deep neural network-based recognition system without modifying the structure of the network itself are investigated. Quantitative results are presented on the challenging IJB-A identification dataset using a state of the art recognition pipeline as a baseline.