Visual homograph: A novel basic visual element

doi:10.1016/j.neucom.2016.04.057

	Visual homograph: A novel basic visual element
	Zhang, Liyan 1,3; Gao, Ke 2
	2016-10-05
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	208 页码:342-349
摘要	The bag-of-visual-words (BoW) model has been broadly applied to represent images in a variety of image retrieval applications. Ideal visual word vocabulary should obtain two important properties, completeness and distinctiveness (i.e., containing all the similar image patches and eliminating different ones accurately). However, the traditional definition of basic visual elements tend to lack in either generality or particularity, which will lead to the incoherence problem and further ruin the image retrieval performance. To address this issue, in this paper, we propose a novel basic visual element called Visual Homograph - groups of local patches which have indivisible descriptors but differ in origins. To generate Visual Homograph based vocabulary, we also propose a novel similarity metric named Integrated Perceptual Similarity which systematically combines center-based and boundary-based measures. Experimental results on standard datasets demonstrate the superiority of Visual Homograph based method over state-of-the-art visual vocabulary generation approaches, in terms of alleviating incoherence problem, and enhancing retrieval performance in practical applications. (C) 2016 Elsevier B.V. All rights reserved.
关键词	Image retrieval Integrated Perceptual Similarity Visual Homographs
DOI	10.1016/j.neucom.2016.04.057
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[61572252] ; National Science Foundation of Jiangsu Province[BK20150755] ; National Science Foundation of Jiangsu Province[BK20150754]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000382794300035
出版者	ELSEVIER SCIENCE BV
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/8094
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Liyan
作者单位	1.Nanjing Univ Aeronaut & Astronaut, Coll Comp Sci & Technol, Nanjing, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100864, Peoples R China 3.Collaborat Innovat Ctr Novel Software Technol & I, Nanjing, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Liyan,Gao, Ke. Visual homograph: A novel basic visual element[J]. NEUROCOMPUTING,2016,208:342-349.
APA	Zhang, Liyan,&Gao, Ke.(2016).Visual homograph: A novel basic visual element.NEUROCOMPUTING,208,342-349.
MLA	Zhang, Liyan,et al."Visual homograph: A novel basic visual element".NEUROCOMPUTING 208(2016):342-349.