A Feature Similarity-Based Multi-Resolution Method for Image Registration

DOI

10.2991/cimns-16.2016.10How to use a DOI?

Keywords

image registration; GHM multi-wavelet; feature extraction; feature similarity; invariant descriptor

Abstract

We present a method to automatically register images based on feature similarity and image decomposing by multiple wavelet-transform. We use GHM multi-wavelet to decompose the image, then use mean-shift image segmentation algorithm to extract the image feature. We serve the regional features as matching primitives, and put forward an improved image registration method based on invariant descriptor. The experimental results show that the algorithm in reducing computational complexity and enhance the algorithm's robustness can get better effect.

Copyright

© 2016, 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  - Zhihui Wang
AU  - Yuzhu Xie
AU  - Yuejiao Fan
AU  - Wenbo Xu
AU  - Qila Sa
AU  - Jinlin Li
PY  - 2016/09
DA  - 2016/09
TI  - A Feature Similarity-Based Multi-Resolution Method for Image Registration
BT  - Proceedings of the 2016 International Conference on Communications, Information Management and Network Security
PB  - Atlantis Press
SP  - 37
EP  - 42
SN  - 2352-538X
UR  - https://doi.org/10.2991/cimns-16.2016.10
DO  - 10.2991/cimns-16.2016.10
ID  - Wang2016/09
ER  -