Face image set classification with self-weighted latent sparse discriminative learning
- PDF / 1,442,738 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 108 Downloads / 202 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S.I. : NEW TRENDS OF NEURAL COMPUTING FOR ADVANCED APPLICATIONS
Face image set classification with self-weighted latent sparse discriminative learning Yuan Sun1 • Zhenwen Ren1,2
•
Chao Yang1 • Quansen Sun2 • Liwan Chen3 • Yanglong Ou1
Received: 1 September 2020 / Accepted: 26 October 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Since image set classification has strong power to overcome various variations in illumination, expression, pose, and so on, it has drawn extensive attention in recent years. Noteworthily, the point-to-point distance-based methods have achieved the promising performance, which aim to compute the similarity between each gallery set and the probe set for classification purpose. Nevertheless, these existing methods have to face the following problems: (1) they do not take full advantage of the between-set discrimination information; (2) they ideally presume that the importance of different gallery sets is equal, whereas this always violates objective facts and may degenerate algorithm performance in practice; (3) they tend to have high computational cost and several parameters, though explicit sparsity can enhance discrimination. To address these problems, we propose a novel method for face image set classification, namely self-weighted latent sparse discriminative learning (SLSDL). Specifically, a novel self-weighted strategy guided discrimination term is proposed to largely boost the discrimination of different gallery sets, such that the effect of true sets can be boosted while the effect of false sets can be weakened or removed. Moreover, we propose a latent sparse normalization to reduce computational complexity as well as the number of trade-off parameters. In addition, we propose an efficient optimization algorithm to solve the final SLSDL. Comprehensive experiments on four public benchmark datasets demonstrate that SLSDL is superior to the state-of-the-art competitors. Keywords Image set classification Face recognition Video-based face classification Sparse representation
1 Introduction With the rapid improvement in computer vision, it is greatly easy to collect multiple faces images in real-life application [1]. Hence, image set model becomes one of
& Zhenwen Ren [email protected] & Chao Yang [email protected] 1
Department of National Defence Science and Technology, Southwest University of Science and Technology, Mianyang 621010, China
2
Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
3
Department of Electronic and Information Engineering, Chongqing Three Gorges University, Chongqing 404199, China
the research hotspots in recent years, where each set consists of multiple images corresponding to a subject. Theoretically, image set can utilize more face information of the same subject to effectively decrease the impact of a mount of appearance variations about expression, pose, illumination, and so on [2, 3], thereby enhancing th
Data Loading...
