Multimodality Medical Image Fusion Algorithm Based on Multi-iteration

DOI

10.2991/meic-14.2014.95How to use a DOI?

Keywords

Medical image;Pixel-level; Multilayer-Fusion; Multi-iteration;

Abstract

Currently, the efficiency of medical image fusion algorithms at pixel level is not very high and the algorithm is limited in the traditional one. Directing at the limitations, this paper put forward the improved algorithm and the multi-layer image fusion algorithm creatively, aiming at improving the quality of the fused image. Multi-layer image fusion algorithm means that, on the basis of the first image fusion, the fused image is fused again with one of the source image, and so on, for many times. It is mainly based on the Pixel gray value weighted average (PIXA) algorithm, Pixel gray value maxima (PIXM) algorithm, Laplacian Pyramid (LP) algorithm and Wavelet Transform (WT) algorithm. Through the comparison of the results of each fusion algorithm and the analysis of the data according to the objective evaluation method of image fusion, it has been found that multi-layer image fusion algorithm, in some ways, is superior to the traditional fusion algorithm. But it is not necessarily that the more times image fusion is conducted, the better the results are. The superiority of two-layer fusion algorithm is particularly more obvious in image clarity, information richness and image correlation, edge keeping degree and image difference.

Copyright

© 2014, 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  - Yin Dai
AU  - Huanzhen Wang
AU  - Kun Yao
AU  - Xuan Wang
PY  - 2014/11
DA  - 2014/11
TI  - Multimodality Medical Image Fusion Algorithm Based on Multi-iteration
BT  - Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 424
EP  - 427
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-14.2014.95
DO  - 10.2991/meic-14.2014.95
ID  - Dai2014/11
ER  -