Abstract
This manuscript focuses on new image segmentation model for
noisy and intensity inhomogeneity images on the basis of natural logarithmic increasing density function. Local image information is necessary
for inhomogeneous images, but it is ineffective for noisy images. As a
result local information misguides the motion of active contour. However, the natural logarithmic function in new proposed model is capable
to capture minute details of images. Moreover, it also reduces the noise in
the images and helps to clarify the exact boundaries. Comparing with local Chan-Vese Model, our new proposed model gives better performance
while treating noisy and intensity inhomogeneity images. Experiments on
noisy and intensity inhomogeneity images show the robustness of our new
proposed model.
Sartaj Ali, Beenesh Dayyan. (2018) Global Image Segmentation Model of Inhomogeneous Noisy Type Images Using Increasing Natural Logarithmic Function, Punjab University Journal of Mathematics, Volume 50, Issue 3.
-
Views
556 -
Downloads
49
Article Details
Volume
Issue
Type
Language
