An Algorithm for Fast Corner Points Extraction with Reducing Mistaken Matching Based on Harris Operator

DOI

10.2991/icmmcce-17.2017.101How to use a DOI?

Keywords

Harris operator; corner detection; NCC algorithm; Ransac algorithm.

Abstract

The paper proposes a new methods which used in image matching Harris corner extraction and corner matching. On the basis of the original Harris algorithm, the efficiency of extracting corners is improved by reducing the number of computing the corner response value. Then the NCC algorithm is used to match the extracted corners, and the matching accuracy is improved by choosing the threshold (auto correlation coefficient). The experimental results show that the proposed algorithm reduces the time of corner extraction, and is superior to the traditional Harris corner extraction method. Moreover, when matching the two images with NCC matching algorithm, the mismatching is reduced. Finally, the Ransac algorithm is used to remove the false matches.

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  - Xiaoyuan Chen
AU  - Yong Zhu
AU  - Bo Xiao
AU  - Yuqiang Dai
AU  - Jin Duan
PY  - 2017/09
DA  - 2017/09
TI  - An Algorithm for Fast Corner Points Extraction with Reducing Mistaken Matching Based on Harris Operator
BT  - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017)
PB  - Atlantis Press
SP  - 542
EP  - 547
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmcce-17.2017.101
DO  - 10.2991/icmmcce-17.2017.101
ID  - Chen2017/09
ER  -