Improving Detection And Recognition Of Degraded Faces By Discriminative Feature Restoration Using GAN

Face detection and recognition in the wild is currently one of the most interesting and challenging problems. Many al- gorithms with high performance have already been proposed and applied in real-world applications. However, the prob- lem of detecting and recognising degraded faces from low- quality images and videos mostly remains unsolved. In this paper, we present an algorithm capable of recovering facial features from very low quality videos and images. The re- sulting output image boosts the performance of existing face detection and recognition algorithms. It contains an effec- tive method involving metric learning and different loss func- tion components operating on different parts of the generator. This enhances the degraded faces by restoring their lost fea- tures rather than its perceptual quality. Our approach has been experimentally proven to enhance face detection and recogni- tion, e.g., the face detection rate is improved by 3.08% for S3FD [1] and the area under the ROC curve for recognition is improved by 2.55% for ArcFace [2] on the SCFace dataset.