CASIA OpenIR  > 类脑智能研究中心
Image classification using boosted local features with random orientation and location selection
Zhang CJ(张淳杰); Cheng J(程健); Zhang YF(张一帆); Liu J(刘静); Liang C(梁超); Pang JB(庞俊彪); Huang QM(黄庆明); Tian Q(田奇)
Source PublicationInformation Sciences
2015
Issue310Pages:118-129
AbstractThe combination of local features with sparse technique has improved
image classification performance dramatically in recent years.
Although very effective, this strategy still has two shortcomings.
First, local features are often extracted in a pre-defined way (e.g.
SIFT with dense sampling) without considering the classification
task. Second, the codebook is generated by sparse coding or its
variants by minimizing the reconstruction error which has no direct
relationships with the classification process. To alleviate the two
problems, we propose a novel boosted local features method with
random orientation and location selection. We first extract local
features with random orientation and location using a weighting
strategy. This randomization process makes us to extract more types
of information for image representation than pre-defined methods.
These extracted local features are then encoded by sparse
representation. Instead of generating the codebook in a single
process, we construct a series of codebooks and the corresponding
encoding parameters of local features using a boosting strategy. The
weights of local features are determined by the classification
performances of learned classifiers. In this way, we are able to
combine the local feature extraction and encoding with classifier
training into a unified framework and gradually improve the image
classification performance. Experiments on several public image
datasets prove the effectiveness and efficiency of the proposed
method.
KeywordSparse Coding Image Classification Random Orientation Boosting Local Feature Selection
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15381
Collection类脑智能研究中心
Affiliation1.School of Computer and Control Engineering, University of Chinese Academy of Sciences
2.Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences
3.National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences
4.National Engineering Research Center for Multimedia Software, School of Computer, Wuhan University
5.Beijing Key Laboratory of Multimedia and Intelligent Software Technology, College of Metropolitan Transportation, Beijing University of Technology
6.Key Lab of Intell. Info. Process, Institute of Computing Technology, Chinese Academy of Sciences
7.Department of Computer Sciences, University of Texas at San Antonio
Recommended Citation
GB/T 7714
Zhang CJ,Cheng J,Zhang YF,et al. Image classification using boosted local features with random orientation and location selection[J]. Information Sciences,2015(310):118-129.
APA Zhang CJ.,Cheng J.,Zhang YF.,Liu J.,Liang C.,...&Tian Q.(2015).Image classification using boosted local features with random orientation and location selection.Information Sciences(310),118-129.
MLA Zhang CJ,et al."Image classification using boosted local features with random orientation and location selection".Information Sciences .310(2015):118-129.
Files in This Item: Download All
File Name/Size DocType Version Access License
1-s2.0-S002002551500(1849KB)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
[Zhang CJ(张淳杰)]'s Articles
[Cheng J(程健)]'s Articles
[Zhang YF(张一帆)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang CJ(张淳杰)]'s Articles
[Cheng J(程健)]'s Articles
[Zhang YF(张一帆)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang CJ(张淳杰)]'s Articles
[Cheng J(程健)]'s Articles
[Zhang YF(张一帆)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 1-s2.0-S0020025515001760-main.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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