Image Projective Invariants

doi:10.1109/TPAMI.2018.2832060

	Image Projective Invariants
	Li, Erbo 1; Mo, Hanlin 2,3; Xu, Dong 4; Li, Hua 2,3
	2019-05-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	41 期号:5 页码:1144-1157
摘要	In this paper, we have proved the existence of projective moment invariants of images using finite combinations of weighted moments, with relative projective differential invariants as weight functions. We have given some instances constructed in that way, and analyzed possible issues could affect the performance. Some procedures are taken to estimate partial derivatives of discrete images, and a new method is designed to normalize the number of pixels for discrete images to minimize the changes before and after the projective transformation. We have carried out experiments using popular image databases and real images to test the performance. And the results show that the invariants proposed in this paper have better stability and discriminability than other previously used moment invariants in image retrieval and classification. Users can directly extract invariant features of images for a given planar object from different viewpoints without knowing the parameters of the 2D projective transformations. Therefore, the projective moment invariant could be potentially useful for planar object recognition, image description and classification.
关键词	2D projective transformation relative projective differential invariant projective weighted moment invariant planar object recognition
DOI	10.1109/TPAMI.2018.2832060
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[60873164] ; National Natural Science Foundation of China[61227802] ; National Natural Science Foundation of China[61379082]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000463607400009
出版者	IEEE COMPUTER SOC
引用统计	被引频次：17[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/2XEOYT63/4272
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Mo, Hanlin
作者单位	1.EON Real Inc, Irvine, CA 92618 USA 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Ambry Genet, Aliso Viejo, CA 92656 USA
推荐引用方式 GB/T 7714	Li, Erbo,Mo, Hanlin,Xu, Dong,et al. Image Projective Invariants[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2019,41(5):1144-1157.
APA	Li, Erbo,Mo, Hanlin,Xu, Dong,&Li, Hua.(2019).Image Projective Invariants.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,41(5),1144-1157.
MLA	Li, Erbo,et al."Image Projective Invariants".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 41.5(2019):1144-1157.