Noise filtering of images is essentially a smoothing process, and it i
s an issue that has been addressed for many years. The most commonly u
sed low-pass filtering methods blur important image structures such as
edges and lines, and thus reduce image contrast and damage image fide
lity. This paper presents a structure adaptive anisotropic filtering t
echnique with its application to processing magnetic resonance images.
It differs from other techniques in that, instead of using local grad
ients as a means of controlling the anisotropism of filters, it uses b
oth a local intensity orientation and an anisotropic measure of level
contours to control the shape and extent of the filter kernel. This en
sures that corners and junctions are well preserved throughout the fil
tering process. The following two aspects of the proposed technique de
monstrate the advantage of using this filtering method. Firstly, the u
se of local orientation detection provides a robust and convenient way
for shaping the filter kernel. Secondly, the structural adaptiveness
of the filtering process ensures that salient image features are non-s
ymmetrically enhanced.