R. Malladi et Ja. Sethian, A UNIFIED APPROACH TO NOISE REMOVAL, IMAGE-ENHANCEMENT, AND SHAPE RECOVERY, IEEE transactions on image processing, 5(11), 1996, pp. 1554-1568
We present a unified approach to noise removal, image enhancement, and
shape recovery in images. The underlying approach relies on the level
set formulation of curve and surface motion, which leads to a class o
f PDE-based algorithms. Beginning with an image, the first stage of th
is approach removes noise and enhances the image by evolving the image
under flow controlled by min/max curvature and by the mean curvature.
This stage is applicable to both salt-and-pepper grey-scale noise and
full-image continuous noise present in black and white images, grey-s
cale images, texture images, and color images. The noise removal/enhan
cement schemes applied in this stage contain only one enhancement para
meter, which in most cases is automatically chosen. The other key adva
ntage of our approach is that a stopping criteria is automatically pic
ked from the image; continued application of the scheme produces no fu
rther change. The second stage of our approach is the shape recovery o
f a desired object; we again exploit the level set approach to evolve
an initial curve/surface toward the desired boundary, driven by an ima
ge-dependent speed function that automatically stops at the desired bo
undary.