CASIA OpenIR  > 类脑智能研究中心
Bundled local features for image representation
Zhang CJ(张淳杰); Sang JT(桑基韬); Zhu GB(朱桂波); Tian Q(田奇)
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
2017
Issue0Pages:0
AbstractLocal features have been widely used for image representation. Traditional methods often treat each local feature independently or simply model the correlations of local features with spatial partition. However, local features are correlated and should be jointly modeled. Besides, due to the variety of images, pre-defined partition rules will probably introduce noisy information. To solve these problems, in this paper, we propose a novel bundled local features method for efficient image representation and apply it for classification. Specially, we first extract local features and bundle them together with over-complete spatial shapes by viewing each local feature as the central point. Then, the most discriminatively bundling features are selected by reconstruction error minimization. The encoding parameters are then used for image representations in a matrix form. Finally, we train bi-linear classifiers with quadratic hinge loss to predict the classes of images. The proposed method can combine local features appropriately and efficiently for discriminative representations. Experimental results on three image datasets show the effectiveness of the proposed method compared with other local features combination strategies.
KeywordBundled Features Image Representation Image Classification Codebook Feature Selection
DOI10.1109/TCSVT.2017.2694060
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15315
Collection类脑智能研究中心
Affiliation1.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Computer and Control Engineering, University of Chinese Academy of Sciences, 100049, Beijing, China
3.School of Computer and Information Technology, Beijing Jiaotong University
4.Department of Computer Sciences, University of Texas at San Antonio. TX, 78249, U.S.A.
Recommended Citation
GB/T 7714
Zhang CJ,Sang JT,Zhu GB,et al. Bundled local features for image representation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2017(0):0.
APA Zhang CJ,Sang JT,Zhu GB,&Tian Q.(2017).Bundled local features for image representation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY(0),0.
MLA Zhang CJ,et al."Bundled local features for image representation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY .0(2017):0.
Files in This Item: Download All
File Name/Size DocType Version Access License
07898795.pdf(1215KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
t-csvt 2 录用邮件.pdf(108KB) 开放获取--View Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang CJ(张淳杰)]'s Articles
[Sang JT(桑基韬)]'s Articles
[Zhu GB(朱桂波)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang CJ(张淳杰)]'s Articles
[Sang JT(桑基韬)]'s Articles
[Zhu GB(朱桂波)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang CJ(张淳杰)]'s Articles
[Sang JT(桑基韬)]'s Articles
[Zhu GB(朱桂波)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 07898795.pdf
Format: Adobe PDF
File name: t-csvt 2 录用邮件.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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