The Research of Image Feature Matching Method Based on CH-SURF

DOI

10.2991/icaise.2013.4How to use a DOI?

Keywords

color Histogram, CH-SURF, feature matching, vs2008

Abstract

Since SURF (Speeded-Up Robust Features) algorithm is designed for gray images in feature extraction and recognition tasks, it can't recognize some objects of similar shape but different color. CH-SURF algorithm is proposed,which combines Color Histogram feature and SURF feature together. CH-SURF algorithm firstly chooses color histogram feature of target image to reach rough localization, then in the defined small pixel region, uses SURF algorithm to achieve feature matching. Finally simulation experiments are carried out under vs2008 platform, and results show that the proposed algorithm has lower computation time than the original SURF. At the same time,it can improve the accuracy of feature matching to some extent.

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  - Zhaodi Wang
AU  - Jicai Deng
PY  - 2013/08
DA  - 2013/08
TI  - The Research of Image Feature Matching Method Based on CH-SURF
BT  - Proceedings of the 2013 The International Conference on Artificial Intelligence and Software Engineering (ICAISE 2013)
PB  - Atlantis Press
SP  - 14
EP  - 17
SN  - 1951-6851
UR  - https://doi.org/10.2991/icaise.2013.4
DO  - 10.2991/icaise.2013.4
ID  - Wang2013/08
ER  -