Perceptual uniform descriptor and ranking on manifold for image retrieval
Liu, Shenglan1,2,3; Wu, Jun1; Feng, Lin1; Qiao, Hong4,5; Liu, Yang2; Luo, Wenbo6; Wang, Wei2
Source PublicationINFORMATION SCIENCES
2018
Volume424Issue:Supplement CPages:235-249
SubtypeArticle
AbstractIncompatibility of image descriptor and ranking has been often neglected in image retrieval. In this paper, Manifold Learning and Gestalt Psychology Theory are involved to solve the problem of incompatibility. A new holistic descriptor called Perceptual Uniform Descriptor (PUD) based on Gestalt psychology is proposed, which combines color and gradient direction to imitate human visual uniformity. PUD features in the same class images distributes on one manifold in most cases, as PUD improves the visual uniformity of the traditional descriptors. Thus, we use manifold ranking and PUD to realize image retrieval. Experiments were carried out on four benchmark data sets, and the proposed method is shown to greatly improve the accuracy of image retrieval. Our experimental results in Uk-bench and Corel-1K datasets demonstrate that N-S score reached 3.58 (HSV 3.4) and mAP at 81.77% (ODBTC 77.9%) respectively by utilizing PUD which has only 280 dimensions. The results are higher than other holistic image descriptors including local ones as well as state-of-the-arts retrieval methods. (C) 2017 Elsevier Inc. All rights reserved.
KeywordManifold Gestalt Psychology Perceptual Uniform Descriptor Ranking Image Retrieval
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.ins.2017.10.010
WOS KeywordNONLINEAR DIMENSIONALITY REDUCTION ; INVARIANT TEXTURE CLASSIFICATION ; LOCAL BINARY PATTERNS ; GRAY-SCALE ; COLOR ; FRAMEWORK ; HISTOGRAM ; FUSION
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of P.R. China(61370200 ; State Key Laboratory of Software Architecture(SKLSAOP1701) ; 61210009 ; 61602082 ; 61672130)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000414889900014
Citation statistics
Cited Times:3[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20102
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Affiliation1.Dalian Univ Technol, Sch Innovat & Entrepreneurship, Dalian 116024, Liaoning, Peoples R China
2.Dalian Univ Technol, Fac Elect Informat & Elect Engn, Dalian 116024, Liaoning, Peoples R China
3.Neusoft Corporat, State Key Lab Software Architecture, Shenyang 110179, Liaoning, Peoples R China
4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
5.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
6.Liaoning Normal Univ, Sch Comp Sci, Dalian 116081, Liaoning, Peoples R China
Recommended Citation
GB/T 7714
Liu, Shenglan,Wu, Jun,Feng, Lin,et al. Perceptual uniform descriptor and ranking on manifold for image retrieval[J]. INFORMATION SCIENCES,2018,424(Supplement C):235-249.
APA Liu, Shenglan.,Wu, Jun.,Feng, Lin.,Qiao, Hong.,Liu, Yang.,...&Wang, Wei.(2018).Perceptual uniform descriptor and ranking on manifold for image retrieval.INFORMATION SCIENCES,424(Supplement C),235-249.
MLA Liu, Shenglan,et al."Perceptual uniform descriptor and ranking on manifold for image retrieval".INFORMATION SCIENCES 424.Supplement C(2018):235-249.
Files in This Item: Download All
File Name/Size DocType Version Access License
Perceptual uniform d(2311KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Shenglan]'s Articles
[Wu, Jun]'s Articles
[Feng, Lin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Shenglan]'s Articles
[Wu, Jun]'s Articles
[Feng, Lin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Shenglan]'s Articles
[Wu, Jun]'s Articles
[Feng, Lin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Perceptual uniform descriptor and ranking on manifold for image retrieval.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.