Robust Face Recognition Based on the Wing Loss and the ℓ1 Penalty

In recent years, face recognition under occluded or corrupted conditions has emerged as a prominent research topic. The advancement in sparse sampling techniques based on regression analysis has provided a novel solution to this challenge. Currently, numerous regression-based sparse sampling models have been investigated by researchers to address this problem. However, the recognition accuracy of most existing models deteriorates significantly when handling heavily occluded or severely corrupted facial images. To overcome this limitation, this paper proposes a wing-constrained sparse coding (WCSC) model and its weighted variant (weighted wing-constrained sparse coding, WWCSC) for robust face recognition in complex scenarios. The corresponding minimization problems are solved using the alternating direction method of multipliers (ADMM) algorithm. Extensive experiments are conducted on four benchmark face databases: the Olivetti Research Laboratory (ORL) database, the Yale database, the AR database and the Face Recognition Technology (FERET) database, to evaluate the proposed method’s performance. Comparative results demonstrate that the WWCSC model maintains superior recognition rates even under challenging conditions involving significant occlusion or corruption, highlighting its remarkable robustness in face recognition tasks. This study provides both theoretical and empirical validation for the effectiveness of the proposed approach.