SIFT Matching with CNN Evidences for Particular Object Retrieval

doi:10.1016/j.neucom.2017.01.081

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 > 新媒体服务与管理技术

	SIFT Matching with CNN Evidences for Particular Object Retrieval
	Zhang Guixuan1,4 ; Zeng Zhi1 ; Zhang Shuwu1 ; Zhang Yuan 2; Wu Wanchun 3
刊名	NEUROCOMPUTING
	2017-05-17
卷号	238 期号:238 页码:399-409
关键词	Particular Object Retrieval Bag-of-words Sift Matching Convolutional Neural Networks
DOI	10.1016/j.neucom.2017.01.081
文献子类	Article
英文摘要	Many object instance retrieval systems are typically based on matching of local features, such as SIFT. However, these local descriptors serve as low-level clues, which are not sufficiently distinctive to prevent false matches. Recently, deep convolutional neural networks (CNN) have shown their promise as a semantic-aware representation for many computer vision tasks. In this paper, we propose a novel approach to employ CNN evidences to improve the SIFT matching accuracy, which plays a critical role in improving the object retrieval performance. To weaken the interference of noise, we extract compact CNN representations from a number of generic object regions. Then a query-adaptive method is proposed to choose appropriate CNN evidence to verify each pre-matched SIFT pair. Two different visual matching verification functions are introduced and evaluated. Moreover, we investigate the suitability of fine-tuning the CNN for our proposed approach. Extensive experiments on benchmark dataSets demonstrate the effectiveness of our method for particular object retrieval. Our results compare favorably to the state-of-the-art methods with acceptable memory usage and query time. (C) 2017 Elsevier B.V. All rights reserved.
WOS关键词	NEAREST-NEIGHBOR SEARCH ; IMAGE RETRIEVAL ; SCALE ; SIMILARITY
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000397372100035
资助机构	National Science and Technology Supporting Program of China(2015BAH49F01) ; Key Technology R&D Program of Beijing(D161100005216001)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14307]
专题	数字内容技术与服务研究中心_新媒体服务与管理技术
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Alibaba Grp, Beijing, Peoples R China 3.Chongqing Med Univ, Childrens Hosp, Chongqing, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhang Guixuan,Zeng Zhi,Zhang Shuwu,et al. SIFT Matching with CNN Evidences for Particular Object Retrieval[J]. NEUROCOMPUTING,2017,238(238):399-409.
APA	Zhang Guixuan,Zeng Zhi,Zhang Shuwu,Zhang Yuan,&Wu Wanchun.(2017).SIFT Matching with CNN Evidences for Particular Object Retrieval.NEUROCOMPUTING,238(238),399-409.
MLA	Zhang Guixuan,et al."SIFT Matching with CNN Evidences for Particular Object Retrieval".NEUROCOMPUTING 238.238(2017):399-409.