Robust sparse representation based face recognition in an adaptive weighted spatial pyramid structure

• Published in: Science China. Information sciences Vol. 61; no. 1; pp. 82 - 94
• Main Authors: Ma, Xiao, Zhang, Fandong, Li, Yuelong, Feng, Jufu
• Format: Journal Article
• Language: English
• Published: Beijing Science China Press 2018; Springer Nature B.V
• Subjects: Classification; Computer Science; Face recognition; Information Systems and Communication Service; Misalignment; Representations; Research Paper; Robustness; face recognition; self-adaptive weighted aggregating; spatial pyramid structure; sparse representation; local robust strategies
• ISSN: 1674-733X; 1869-1919
• DOI: 10.1007/s11432-016-9009-6

The sparse representation based classification methods has achieved significant performance in recent years. To fully exploit both the holistic and locality information of face samples, a series of sparse representation based methods in spatial pyramid structure have been proposed. However, there are still some limitations for these sparse representation methods in spatial pyramid structure. Firstly, all the spatial patches in these methods are directly aggregated with same weights, ignoring the differences of patches＇ reliability. Secondly, all these methods are not quite robust to poses, expression and misalignment variations, especially in under-sampled cases. In this paper, a novel method named robust sparse representation based classification in an adaptive weighted spatial pyramid structure（RSRC-ASP） is proposed. RSRC-ASP builds a spatial pyramid structure for sparse representation based classification with a self-adaptive weighting strategy for residuals＇ aggregation. In addition, three strategies, local-neighbourhood representation, local intra-class Bayesian residual criterion, and local auxiliary dictionary, are exploited to enhance the robustness of RSRC-ASP. Experiments on various data sets show that RSRC-ASP outperforms the classical sparse representation based classification methods especially for under-sampled face recognition problems.