We describe a new image fusion paradigm that provides an
enhanced image from a set of source images that present regions with
different spatial degradation patterns. The fusion procedure is based on
the use of a new defocusing pixel-level measure. Such a measure is
defined through a 1-D pseudo-Wigner distribution function (PWD) applied
to nonoverlapping N-pixel window slices of the original image. The
process is repeated to cover the full image size. By taking a lowresolution
image as a reference image, which can be defined by blurring
and averaging the two source images, a pixel-level distance measure of
the defocus degree can be obtained from the PWD of each image. This
procedure makes it possible to choose from a focusing point of view the
in-focus pixels from each one of the given source images. The method is
illustrated with different pairs of images of the same scene, which are
partly focused and partly defocused in different regions. The image fusion
approach that we propose here can work for any source of images
available, and the comparison using evaluation measures such as mean
square error or percentage of correct decisions shows that our framework
can outperform the current approaches for the analyzed cases.
One additional advantage of the present approach is its reduced computational
cost when compared with other methods based on a full
2-D implementation of the PWD.
Salvador Gabarda (2021). mapfusion (https://www.mathworks.com/matlabcentral/fileexchange/53587-mapfusion), MATLAB Central File Exchange. Retrieved .
MATLAB Release Compatibility
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!