Patch-Set-Based Representation for Alignment-Free Image Set Classification

doi:10.1109/TCSVT.2015.2469571

	Patch-Set-Based Representation for Alignment-Free Image Set Classification
	Shenghua Gao1 ; Zinan Zeng 2; Kui Jia 3; Tsung-Han Chan 4; Jinhui Tang 5
	2016-09
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (IF:8.3[JCR-2023],7.1[5-Year])
ISSN	1051-8215
卷号	26 期号:9 页码:1646-1658
发表状态	已发表
DOI	10.1109/TCSVT.2015.2469571
摘要	This paper presents a patch-set-based sparse representation for image set classification. Compared with image-based image set representation, our patch-set-based representation is alignment free and thus has an advantage for tasks like video-based face recognition, image-set-based object recognition, and video-based hand gesture recognition, where precious alignment is usually difficult or even impossible due to large variance in view angle or pose. Specifically, to bypass the alignment issue, we propose to adopt the patch-based image set representation by dividing each image within each set into patches, then we cluster all the training patches into multiple clusters and classify the test patches based on the cluster centers of training patches. The labels of test patches within each cluster are inferred from a patch-set-based sparse representation for classification, and the labels of all test patches from all the clusters are then aggregated to predict a single label for the test set. Experimental results on video-based face recognition data sets (CMU-MoBo and YouTube Celebrities), image-set-based object recognition data set (ETH-80), and video-based hand gesture recognition data set (Kinect Hand Gestures) demonstrate that our proposed method consistently outperforms all existing ones, and the improvement is very significant on the YouTube Celebrities and Kinect Hand Gesture data sets. Moreover, we also quantitatively show the robustness of our method to misalignment on the Mutli-PIE data set.
关键词	Alignment free image set classification patch-set-based representation video-based face recognition
URL	查看原文
收录类别	SCI ; EI
语种	英语
资助项目	National Natural Science Foundation of China[61502304]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000384078400006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20163702808409
EI主题词	Alignment ; Classification (of information) ; Face recognition ; Gesture recognition ; Object recognition ; Optical character recognition ; Palmprint recognition
EI分类号	Mechanical Devices:601.1 ; Information Theory and Signal Processing:716.1 ; Computer Applications:723.5 ; Light/Optics:741.1
WOS关键词	FACE RECOGNITION ; APPEARANCE
原始文献类型	Article
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/1720
专题	信息科学与技术学院_PI研究组_高盛华组
作者单位	1.ShanghaiTech University, Shanghai, China 2.Advanced Digital Sciences Center, Singapore 3.University of Macau, Macau, China 4.MediaTek Inc., Hsinchu, Taiwan 5.Nanjing University of Science and Technology, Nanjing, China
第一作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Shenghua Gao,Zinan Zeng,Kui Jia,et al. Patch-Set-Based Representation for Alignment-Free Image Set Classification[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2016,26(9):1646-1658.
APA	Shenghua Gao,Zinan Zeng,Kui Jia,Tsung-Han Chan,&Jinhui Tang.(2016).Patch-Set-Based Representation for Alignment-Free Image Set Classification.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,26(9),1646-1658.
MLA	Shenghua Gao,et al."Patch-Set-Based Representation for Alignment-Free Image Set Classification".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 26.9(2016):1646-1658.