Robust face recognition based on the wing loss and the $\ell_1$ regularization

TL;DR

The paper addresses robust face recognition under occlusion and damage by proposing wing loss–based sparse coding methods. It introduces a wing loss–based wing constrained sparse coding (WCSC) and its weighted variant (WWCSC), optimized via ADMM, with a weight mechanism that downweights outliers and a per-class residual-based classifier. The approaches are evaluated on ORL, Yale, AR, and FERET datasets, showing that WWCSC achieves high recognition rates under heavy occlusion and corruption, often outperforming several baselines and approaching the performance of IRGSC on challenging data. The work provides a practical, robust sparse-coding framework for real-world face recognition tasks in noisy environments, enhanced by dimensionality reduction via random projection.

Abstract

In recent years, sparse sampling techniques based on regression analysis have witnessed extensive applications in face recognition research. Presently, numerous sparse sampling models based on regression analysis have been explored by various researchers. Nevertheless, the recognition rates of the majority of these models would be significantly decreased when confronted with highly occluded and highly damaged face images. In this paper, a new wing-constrained sparse coding model(WCSC) and its weighted version(WWCSC) are introduced, so as to deal with the face recognition problem in complex circumstances, where the alternating direction method of multipliers (ADMM) algorithm is employed to solve the corresponding minimization problems. In addition, performances of the proposed method are examined based on the four well-known facial databases, namely the ORL facial database, the Yale facial database, the AR facial database and the FERET facial database. Also, compared to the other methods in the literatures, the WWCSC has a very high recognition rate even in complex situations where face images have high occlusion or high damage, which illustrates the robustness of the WWCSC method in facial recognition.

Figures (3)

• Figure 1: Face images with different percentages of pixel corruption(from 0% to 50%).
• Figure 2: Face images of a white block occlusion(from 50% to 90%).
• Figure 3: Face images of a black block occlusion(from 50% to 90%).