Receptive Fields Selection for Binary Feature Description

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	Receptive Fields Selection for Binary Feature Description
	Fan, Bin1 ; Kong, Qingqun2 ; Trzcinski, Tomasz 3; Wang, Zhiheng 4; Pan, Chunhong1 ; Fua, Pascal 3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2014-06-01
卷号	23 期号:6 页码:2583-2595
关键词	Local invariant descriptor binary descriptor image matching local receptive field object recognition
英文摘要	Feature description for local image patch is widely used in computer vision. While the conventional way to design local descriptor is based on expert experience and knowledge, learning-based methods for designing local descriptor become more and more popular because of their good performance and data-driven property. This paper proposes a novel data-driven method for designing binary feature descriptor, which we call receptive fields descriptor (RFD). Technically, RFD is constructed by thresholding responses of a set of receptive fields, which are selected from a large number of candidates according to their distinctiveness and correlations in a greedy way. Using two different kinds of receptive fields (namely rectangular pooling area and Gaussian pooling area) for selection, we obtain two binary descriptors RFDR and RFDG accordingly. Image matching experiments on the well-known patch data set and Oxford data set demonstrate that RFD significantly outperforms the state-of-the-art binary descriptors, and is comparable with the best float-valued descriptors at a fraction of processing time. Finally, experiments on object recognition tasks confirm that both RFDR and RFDG successfully bridge the performance gap between binary descriptors and their floating-point competitors.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]	Computer Science ; Engineering
关键词[WOS]	TEXTURE ; CLASSIFICATION ; PATTERNS ; KERNELS ; CODES
收录类别	SCI
语种	英语
WOS记录号	WOS:000336041500009
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/2777]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Ecole Polytech Fed Lausanne, Comp Vis Lab, CH-1015 Lausanne, Switzerland 4.Henan Polytech Univ, Sch Comp Sci & Tech, Jiaozuo 454150, Peoples R China
推荐引用方式 GB/T 7714	Fan, Bin,Kong, Qingqun,Trzcinski, Tomasz,et al. Receptive Fields Selection for Binary Feature Description[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2014,23(6):2583-2595.
APA	Fan, Bin,Kong, Qingqun,Trzcinski, Tomasz,Wang, Zhiheng,Pan, Chunhong,&Fua, Pascal.(2014).Receptive Fields Selection for Binary Feature Description.IEEE TRANSACTIONS ON IMAGE PROCESSING,23(6),2583-2595.
MLA	Fan, Bin,et al."Receptive Fields Selection for Binary Feature Description".IEEE TRANSACTIONS ON IMAGE PROCESSING 23.6(2014):2583-2595.