Image Matching Algorithm Based on Contourlet Transform and VA Fast Search

DOI

10.2991/eeic-13.2013.105How to use a DOI?

Keywords

sift; contourlet; VA; Image matching

Abstract

This article aim at the application of the high real-time required embedded terminal situation, an improved SIFT algorithm is proposed. After traditional SFIT algorithm get the stable points, global texture description was carried out on the key points of frequency domain by contourlet transform, select the top 1% of points, and then through a kind of nearest neighbor search algorithm based on Vector Angle (Vector Angle, VA) to match. This algorithm improves precision, speed and the accuracy of the embedded terminal.

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  - Jie Fu
AU  - Pei Wang
AU  - Yan He
AU  - Xiao-qing Xu
PY  - 2013/12
DA  - 2013/12
TI  - Image Matching Algorithm Based on Contourlet Transform and VA Fast Search
BT  - Proceedings of the 3rd International Conference on Electric and Electronics
PB  - Atlantis Press
SP  - 446
EP  - 449
SN  - 1951-6851
UR  - https://doi.org/10.2991/eeic-13.2013.105
DO  - 10.2991/eeic-13.2013.105
ID  - Fu2013/12
ER  -