Naturally combined shape-color moment invariants under affine transformations
Gong, Ming1,2,3,4,5; Hao, You2,3; Mo, Hanlin2,3; Li, Hua2,3
刊名COMPUTER VISION AND IMAGE UNDERSTANDING
2017-09-01
卷号162页码:46-56
关键词Invariants Color Shape Descriptor Dual-affine transformations
ISSN号1077-3142
DOI10.1016/j.cviu.2017.07.003
英文摘要We proposed a kind of naturally combined shape-color affine moment invariants (SCAMI), which consider both shape and color affine transformations simultaneously in one single system. In the real scene, color and shape deformations always exist in images simultaneously. Simple shape invariants or color invariants cannot be qualified for this situation. The conventional method is just to make a simple linear combination of the two factors. Meanwhile, the manual selection of weights is a complex issue. Our construction method is based on the multiple integration framework. The integral kernel is assigned as the continued product of the shape and color invariant cores. It is the first time to directly derive an invariant to dual affine transformations of shape and color. The manual selection of weights is no longer necessary, and both the shape and color transformations are extended to affine transformation group. With the various of invariant cores, a set of lower-order invariants are constructed and the completeness and independence are discussed detailed. A set of SCAMIs, which called SCAMI24, are recommended, and the effectiveness and robustness have been evaluated on both synthetic and real datasets. (C) 2017 Elsevier Inc. All rights reserved.
资助项目National Science Foundation of China[61379082] ; National Science Foundation of China[61227802]
WOS研究方向Computer Science ; Engineering
语种英语
出版者ACADEMIC PRESS INC ELSEVIER SCIENCE
WOS记录号WOS:000412965200004
内容类型期刊论文
源URL[http://119.78.100.204/handle/2XEOYT63/6862]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Hao, You
作者单位1.Inst Comp Technol, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, 6 Acad Sci South Rd, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
4.Microsoft Search Technol Ctr Asia, AI & Res Grp, Beijing, Peoples R China
5.Microsoft AI & Res Grp, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Gong, Ming,Hao, You,Mo, Hanlin,et al. Naturally combined shape-color moment invariants under affine transformations[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2017,162:46-56.
APA Gong, Ming,Hao, You,Mo, Hanlin,&Li, Hua.(2017).Naturally combined shape-color moment invariants under affine transformations.COMPUTER VISION AND IMAGE UNDERSTANDING,162,46-56.
MLA Gong, Ming,et al."Naturally combined shape-color moment invariants under affine transformations".COMPUTER VISION AND IMAGE UNDERSTANDING 162(2017):46-56.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace