Deakin University
Browse

Object categorization via sparse representation of local features

conference contribution
posted on 2012-01-01, 00:00 authored by Jin Wang, S Xiangping, Ronghua Chen, Fenghua She, Q Wang
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.

History

Event

International Conference on Pattern Recognition (21st : 2012 : Tsukuba, Japan)

Pagination

3005 - 3008

Publisher

IEEE

Location

Tsukuba, Japan

Place of publication

[Tsukuba, Japan]

Start date

2012-11-11

End date

2012-11-15

ISSN

1051-4651

ISBN-13

9784990644109

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2012, ICPR

Title of proceedings

ICPR 2012 : Proceedings of the 21st International Conference on Pattern Recognition