Remote sensing image fusion based on shearlet and genetic algorithm
by Qiguang Miao; Ruyi Liu; Yining Quan; Jianfeng Song
International Journal of Bio-Inspired Computation (IJBIC), Vol. 9, No. 4, 2017

Abstract: Image fusion is to combine information from two or more images of a scene into a single composite image, which will produce more information for visual perception or computer processing. In recent years, many algorithms have been developed, but there exist information loss and image distortion. To produce a satisfactory fusion result, an image fusion algorithm based on shearlet and genetic algorithm is proposed. As one of the multi-scale geometric analysis (MGA) tools, shearlet is equipped with a rich mathematical structure which is associated to a multi-resolution analysis. Genetic algorithm (GA) is an optimisation algorithm. So GA can be used to image fusion where parameter optimisation is required. Firstly, shearlet is performed on each input image to obtain their low-pass and high-pass coefficients. And then, GA is used to optimise the weighted factors in the fusion rule. Finally, the fused image is obtained by inverse shearlet transform. Experimental results have demonstrated that our method could acquire better fusion quality than any other methods.

Online publication date: Mon, 05-Jun-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bio-Inspired Computation (IJBIC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com