Robust linear representation via exploiting structure prior

doi:10.1016/j.patcog.2017.08.027

CASIA OpenIR > 智能感知与计算研究中心

	Robust linear representation via exploiting structure prior
	Wang, Dong; He, Ran; Wang, Liang; Tan, Tieniu
发表期刊	PATTERN RECOGNITION
	2018-04-01
卷号	76 期号:NA 页码:560-568
文章类型	Article
摘要	Over the past few years, linear representation models have seen a lot of successful applications such as face recognition in computer vision. In the context of face recognition, occlusion is a key factor that often curbs the performance of practical face recognition systems. In this paper, we propose to alleviate such negative influence of the occlusion noises by explicitly encoding the spatial continuity prior of the occlusion. Given the fact that many real-world occlusions such as sunglasses and scarves are contiguous, taking such prior into account can help build a more accurate model and achieve higher recognition rates. Besides, a general framework has also been proposed in which many off-the-shelf linear representation models can be nicely incorporated. And the minimization objectives of all these models can be solved via the same Half-Quadratic optimization procedure. Therefore the robustness of these models to occlusions can be comprehensively evaluated on a fair platform. Extensive experiments on the AR and Extended Yale B face databases corroborate that the proposed algorithms can improve the model robustness to contiguous occlusions. (C) 2017 Elsevier Ltd. All rights reserved.
关键词	Linear Representation Half-quadratic Optimization Occlusion Prior
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.patcog.2017.08.027
关键词[WOS]	FACE RECOGNITION ; SPARSE REPRESENTATION ; SUBSPACES
收录类别	SCI
语种	英语
项目资助者	National Basic Research Program of China(2012CB316302)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000424853800041
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21078
专题	智能感知与计算研究中心
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Dong,He, Ran,Wang, Liang,et al. Robust linear representation via exploiting structure prior[J]. PATTERN RECOGNITION,2018,76(NA):560-568.
APA	Wang, Dong,He, Ran,Wang, Liang,&Tan, Tieniu.(2018).Robust linear representation via exploiting structure prior.PATTERN RECOGNITION,76(NA),560-568.
MLA	Wang, Dong,et al."Robust linear representation via exploiting structure prior".PATTERN RECOGNITION 76.NA(2018):560-568.