Image Processing Reference
In-Depth Information
Chapter 7
Optimization-Based Fusion
7.1 Introduction
We have explored three hyperspectral image fusion techniques in the earlier chapters
of the topic. We have also reviewed several other hyperspectral image fusion tech-
niques in Chap. 2 alongwith a brief overviewof a number of generalized image fusion
schemes. The common feature of most of the existing fusion methodologies is that
the fusion rule operates over spatial characteristics of the input images (or hyperspec-
tral bands) to define the fusion weights. Fusion weights which have been calculated
from some kind of saliency measure of the pixel, determine the effective contribu-
tion of the corresponding pixel toward the final result. Thus, the characteristics of
the input data control the process of fusion, and hence, the resultant-fused image. As
mentioned earlier, in this monograph, we are focused on obtaining the fused image
for the purpose of visualization of the scene contents. In such a case, would it not
be highly desirable that the fused image should possess certain characteristics to
facilitate a better visualization and interpretation of the scene? In other words, it is
beneficial to have a fusion scheme that takes into consideration the characteristics of
the output, rather than focusing on the input characteristics as was done in previous
chapters. Although we have considered smoothness of the fused image, we have not
given specific attention to any other qualities the fused image should possess. In
this chapter, we explain some of the desired elements of the image quality. Then we
explain the formulation of a multi-objective cost function based on some of these ele-
ments. This cost function has been developed into the variational framework which
has been explained in the previous chapter (Sect. 6.2 , Chap. 6 ) . Finally, we discuss
how an iterative solution can be formed using the Euler-Lagrange equation.
The next section discusses various aspects of image quality, and their usage in
image enhancement. The multi-objective cost function, and its solution are pro-
vided in Sect. 7.3 . The corresponding details of implementation are given in Sect. 7.4 .
Results of fusion are illustrated in Sect. 7.5 . Finally, Sect. 7.6 brings out the summary.
Search WWH ::

Custom Search