The Processing Method and Application of Medical Image with Feature Points Matching

DOI

10.2991/amcce-15.2015.128How to use a DOI?

Keywords

feature points matching; medical images; registration; correlation coefficient

Abstract

In this thesis, the registration method of medical image is based on feature points, and mainly starting from the feature extraction operator. It makes comparative studies on the aspects of accuracy, stability and so on. Through theoretical and experimental studies, we make improvements on algorithm. Feature points matching in this thesis regards feature point neighborhood gray scale correlation as the similarity measure, uses affine transformation of space to search space, and utilizes affine invariance of Mahalanobis distance correcting feature point matching so as to the optimization of parameters. Experimental results show that the improvement method of extraction operator based on Harris in this thesis makes a good effect on some certain kind of medical images.

Copyright

© 2015, 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  - Zhongyong Tian
PY  - 2015/04
DA  - 2015/04
TI  - The Processing Method and Application of Medical Image with Feature Points Matching
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SP  - 1312
EP  - 1318
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.128
DO  - 10.2991/amcce-15.2015.128
ID  - Tian2015/04
ER  -