TY - GEN
T1 - Improving Detection And Recognition Of Degraded Faces By Discriminative Feature Restoration Using GAN
AU - Ghosh, Soumya Shubhra
AU - Hua, Yang
AU - Mukherjee, Sankha Subhra
AU - Robertson, Neil M.
PY - 2020/9/30
Y1 - 2020/9/30
N2 - 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.
AB - 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.
U2 - 10.1109/ICIP40778.2020.9191246
DO - 10.1109/ICIP40778.2020.9191246
M3 - Conference contribution
SN - 978-1-7281-6396-3
T3 - IEEE International Conference on Image Processing (ICIP): Proceedings
SP - 2146
EP - 2150
BT - 2020 IEEE International Conference on Image Processing (ICIP): Proceedings
PB - IEEE
ER -