SIFT Matching with CNN Evidences for Particular Object Retrieval

doi:10.1016/j.neucom.2017.01.081

CASIA OpenIR > 数字内容技术与服务研究中心 > 版权智能与文化计算

	SIFT Matching with CNN Evidences for Particular Object Retrieval
	Zhang Guixuan1,4 ; Zeng Zhi1 ; Zhang Shuwu1 ; Zhang Yuan2 ; Wu Wanchun 3
发表期刊	NEUROCOMPUTING
	2017-05-17
卷号	238 期号:238 页码:399-409
文章类型	Article
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.
关键词	Particular Object Retrieval Bag-of-words Sift Matching Convolutional Neural Networks
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2017.01.081
关键词[WOS]	NEAREST-NEIGHBOR SEARCH ; IMAGE RETRIEVAL ; SCALE ; SIMILARITY
收录类别	SCI
语种	英语
项目资助者	National Science and Technology Supporting Program of China(2015BAH49F01) ; Key Technology R&D Program of Beijing(D161100005216001)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000397372100035
引用统计	被引频次：23[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14307
专题	数字内容技术与服务研究中心_版权智能与文化计算
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
第一作者单位	中国科学院自动化研究所
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.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
SIFT Matching with C（2393KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览