Ordinal pyramid coding for rotation invariant feature extraction

doi:10.1016/j.neucom.2017.02.071

	Ordinal pyramid coding for rotation invariant feature extraction
	Wang, Guoli1,2 ; Fan, Bin1 ; Zhou, Zhili 3,4; Pan, Chunhong1
刊名	NEUROCOMPUTING
	2017-06-14
卷号	242 期号:242 页码:150-160
关键词	Rotation Invariant Ordinal Pyramid Pooling Fisher Vector Feature Extraction
DOI	10.1016/j.neucom.2017.02.071
文献子类	Article
英文摘要	This paper proposes a novel rotation invariant feature for object recognition. Firstly, the local Fourier transform features of pixels in the described region are encoded by Fisher Vectors. Then, the encoded vectors are aggregated into a final representation by ordinal pyramid pooling, which hierarchically partitions the described region into sub-regions based on the orders of its pixels' rotation invariants. Since both the encoded Fisher Vectors and the ordinal pyramid pooling strategy are rotation invariant, the extracted feature is rotation invariant by nature. Two kinds of rotation invariants are investigated in this framework, one is the Radial Gradient Orientation and the other is the Radial Gradient Angle. Experiments on handwritten digit recognition and airplane/car detection in aerial images demonstrate the effectiveness of the proposed method, which outperforms the state of the art. (C) 2017 Elsevier B.V. All rights reserved.
WOS关键词	REMOTE-SENSING IMAGES ; SCENE CLASSIFICATION ; OBJECT DETECTION ; REPRESENTATION ; RECOGNITION ; EFFICIENT ; NETWORKS ; MODEL ; DEEP ; HOG
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000399859500013
资助机构	National Natural Science Foundation of China(61403375 ; Priority Academic Program Development of Jiangsu Higher Education Institutions ; Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology ; 61472119 ; 61573352 ; 91338202)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14524]
专题	自动化研究所_空天信息研究中心
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhong Guan Cun East Rd, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 101408, Peoples R China 3.Nanjing Univ Informat Sci & Technol, Jiangsu Engn Ctr Network Monitoring, Nanjing 210044, Jiangsu, Peoples R China 4.Nanjing Univ Informat Sci & Technol, Sch Comp & Software, Nanjing 210044, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Wang, Guoli,Fan, Bin,Zhou, Zhili,et al. Ordinal pyramid coding for rotation invariant feature extraction[J]. NEUROCOMPUTING,2017,242(242):150-160.
APA	Wang, Guoli,Fan, Bin,Zhou, Zhili,&Pan, Chunhong.(2017).Ordinal pyramid coding for rotation invariant feature extraction.NEUROCOMPUTING,242(242),150-160.
MLA	Wang, Guoli,et al."Ordinal pyramid coding for rotation invariant feature extraction".NEUROCOMPUTING 242.242(2017):150-160.