Rotative maximal pattern: A local coloring descriptor for object classification and recognition

doi:10.1016/j.ins.2017.04.011

	Rotative maximal pattern: A local coloring descriptor for object classification and recognition
	Pang, Junbiao 1; Huang, Jing 1; Qin, Lei 3; Zhang, Weigang 4; Qing, Laiyun 2; Huang, Qingming 2,3; Yin, Baocai 1
	2017-09-01
发表期刊	INFORMATION SCIENCES
ISSN	0020-0255
卷号	405 页码:190-206
摘要	Inspired by the photometric invariance of color space, this paper proposes a simple yet powerful descriptor for object detection and recognition, called Rotative Maximal Pattern (RMP). The effectiveness of RMP comes from the two components: Rotatable Couple Templates (RCTs) with max pooling, and Normalized Histogram Intersection (NHI) with the theoretical guarantee. More concretely, RCTs are the combination of two templates to code the possible rotations. NHI serves as the similarity between two color histograms. We have conducted extensive experiments on INRIA pedestrian and Pascal VOC2007 data sets for object detection tasks; we also show that our approach leads to a promising performance on Caltech 101, Scene 15, UIUCsport and Stanford 40 action data sets. (C) 2017 Published by Elsevier Inc.
关键词	Object detection Object recognition Max pooling Translation invariance Self similarity Photometric invariance
DOI	10.1016/j.ins.2017.04.011
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[61672069] ; Natural Science Foundation of China[61332016] ; Natural Science Foundation of China[61620106009] ; Natural Science Foundation of China[61472387] ; Natural Science Foundation of China[U1636214] ; Natural Science Foundation of China[61650202] ; Key Research Program of Frontier Sciences[CAS: QYZDJ-SSW-SYS013] ; China Postdoctoral Science Foundation ; Beijing Post-Doctoral Research Foundation ; Beijing Municipal Commission of Education[KM201610005034] ; Funding Project for Academic Human Resources Development in Institutions of Higher Learning Under the Jurisdiction of Beijing Municipality (PHR)
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000401688100012
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7245
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Qing, Laiyun
作者单位	1.Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Multimedia & Intelligent Software, 100 Pingleyuan Rd, Chaoyang Dist 100124, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, 19 Yuquan Rd, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China 4.Harbin Inst Technol Weihai, Sch Comp Sci & Technol, 2 West Wenhua Rd, Weihai 26209, Peoples R China
推荐引用方式 GB/T 7714	Pang, Junbiao,Huang, Jing,Qin, Lei,et al. Rotative maximal pattern: A local coloring descriptor for object classification and recognition[J]. INFORMATION SCIENCES,2017,405:190-206.
APA	Pang, Junbiao.,Huang, Jing.,Qin, Lei.,Zhang, Weigang.,Qing, Laiyun.,...&Yin, Baocai.(2017).Rotative maximal pattern: A local coloring descriptor for object classification and recognition.INFORMATION SCIENCES,405,190-206.
MLA	Pang, Junbiao,et al."Rotative maximal pattern: A local coloring descriptor for object classification and recognition".INFORMATION SCIENCES 405(2017):190-206.