Face Synthesis for Eyeglass-Robust Face Recognition
This addresses a specific challenge in face recognition for applications like security or authentication, but it is incremental as it builds on existing synthesis and deep learning methods.
The paper tackles the problem of eyeglasses degrading face recognition accuracy by synthesizing high-fidelity face images with eyeglasses using 3D models, which improves recognition performance on real databases.
In the application of face recognition, eyeglasses could significantly degrade the recognition accuracy. A feasible method is to collect large-scale face images with eyeglasses for training deep learning methods. However, it is difficult to collect the images with and without glasses of the same identity, so that it is difficult to optimize the intra-variations caused by eyeglasses. In this paper, we propose to address this problem in a virtual synthesis manner. The high-fidelity face images with eyeglasses are synthesized based on 3D face model and 3D eyeglasses. Models based on deep learning methods are then trained on the synthesized eyeglass face dataset, achieving better performance than previous ones. Experiments on the real face database validate the effectiveness of our synthesized data for improving eyeglass face recognition performance.