Object categorization via sparse representation of local features

Wang, Jin, Xiangping, Sun, Chen, Ronghua, She, Fenghua (Mary) and Wang, Qiang 2012, Object categorization via sparse representation of local features, in ICPR 2012 : Proceedings of the 21st International Conference on Pattern Recognition, IEEE, [Tsukuba, Japan], pp. 3005-3008.

Attached Files
Name Description MIMEType Size Downloads

Title Object categorization via sparse representation of local features
Author(s) Wang, Jin
Xiangping, Sun
Chen, Ronghua
She, Fenghua (Mary)
Wang, Qiang
Conference name International Conference on Pattern Recognition (21st : 2012 : Tsukuba, Japan)
Conference location Tsukuba, Japan
Conference dates 11-15 Nov. 2012
Title of proceedings ICPR 2012 : Proceedings of the 21st International Conference on Pattern Recognition
Editor(s) [Unknown]
Publication date 2012
Conference series International Conference on Pattern Recognition
Start page 3005
End page 3008
Total pages 4
Publisher IEEE
Place of publication [Tsukuba, Japan]
Keyword(s) bag-of-features
high-level features
local feature
object categorization
object classification
sparse coding
sparse representation
unified framework
Summary Sparse representation has been introduced to address many recognition problems in computer vision. In this paper, we propose a new framework for object categorization based on sparse representation of local features. Unlike most of previous sparse coding based methods in object classification that only use sparse coding to extract high-level features, the proposed method incorporates sparse representation and classification into a unified framework. Therefore, it does not need a further classifier. Experimental results show that the proposed method achieved better or comparable accuracy than the well known bag-of-features representation with various classifiers.
ISBN 9784990644109
ISSN 1051-4651
Language eng
Field of Research 080106 Image Processing
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2012, ICPR
Persistent URL http://hdl.handle.net/10536/DRO/DU:30052845

Document type: Conference Paper
Collections: Centre for Intelligent Systems Research
Institute for Frontier Materials
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 36 Abstract Views, 9 File Downloads  -  Detailed Statistics
Created: Wed, 05 Jun 2013, 11:44:05 EST by Barb Robertson

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.