中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Visual homograph: A novel basic visual element

文献类型:期刊论文

作者Zhang, Liyan1,3; Gao, Ke2
刊名NEUROCOMPUTING
出版日期2016-10-05
卷号208页码:342-349
关键词Image retrieval Integrated Perceptual Similarity Visual Homographs
ISSN号0925-2312
DOI10.1016/j.neucom.2016.04.057
英文摘要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.
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
语种英语
WOS记录号WOS:000382794300035
出版者ELSEVIER SCIENCE BV
源URL[http://119.78.100.204/handle/2XEOYT63/8093]  
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.

入库方式: OAI收割

来源:计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。