The Scale and Characteristics Strength of SURF Feature Points Adaptive Matching Algorithm

DOI

10.2991/ammee-17.2017.166How to use a DOI?

Keywords

Image registration, SURF, scale, feature point.

Abstract

In order to improve the matching precision of the SURF image feature points, we study the relationship among the scale of the SURF feature points, the characteristics of strength and matching precision. Then, a feature point matching algorithm of SURF image feature is proposed, which is adaptive to the feature point scale and characteristic strength. On the basis research of the scale and characteristics strength of SURF feature points, we found that the larger the scale of feature points set, the lower the matching precision will be; and the higher the intensity of characteristic, the matching precision are higher, but the number is less. Therefore, the using of the adaptive algorithm which can match the different scales of feature points with different characteristics strength threshold can keep the balance between the feature point matching precision and the quantity of matching feature points pairs, and realize the high precision of SURF feature points matching. The experimental shows that, compared with the traditional algorithm of SURF, this algorithm can obtain more precise matching feature points pairs.

Copyright

© 2017, 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  - Xiaotong Hu
AU  - Hui Ren
AU  - Nan Liu
PY  - 2017/06
DA  - 2017/06
TI  - The Scale and Characteristics Strength of SURF Feature Points Adaptive Matching Algorithm
BT  - Proceedings of the Advances in Materials, Machinery, Electrical Engineering (AMMEE 2017)
PB  - Atlantis Press
SP  - 870
EP  - 876
SN  - 2352-5401
UR  - https://doi.org/10.2991/ammee-17.2017.166
DO  - 10.2991/ammee-17.2017.166
ID  - Hu2017/06
ER  -