A Robust and Discriminative Feature Representation based on Compact Coding

DOI

10.2991/icmt-13.2013.149How to use a DOI?

Keywords

Visual feature   Feature representation   Compact coding

Abstract

As human vision system works, the visual features extracted from colours, textures, shapes, etc. are complement and should be synthesized to make a decision. Existing applications mainly base on one kind of features such as the wildly used texture feature. We put forward that complement features should be combined together to improve feature discriminabilty. And we propose a feature combining framework, which benefits from the recent fruitful research on compact coding of visual features. The compact codes are learned to be robust to complex image content variations. We combine colour histogram and texture under the framework, and experiments show that our method provides an effective way to the representation of features and has a wide application.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yue Jinpeng
AU  - Jiang Guang
AU  - Hu Hong
AU  - Shi Zhongzhi
PY  - 2013/11
DA  - 2013/11
TI  - A Robust and Discriminative Feature Representation based on Compact Coding
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 1213
EP  - 1220
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.149
DO  - 10.2991/icmt-13.2013.149
ID  - Jinpeng2013/11
ER  -