25-08-2017, 09:32 PM
A New Fuzzy Logic Filter for Image Enhancement
A New Fuzzy Logic Filter.pdf (Size: 1.09 MB / Downloads: 23)
Abstract
This paper presents a new fuzzy-logic-control based
filter with the ability to remove impulsive noise and smooth
Gaussian noise, while, simultaneously, preserving edges and image
details efficiently. To achieve these three image enhancement
goals, we first develop filters that have excellent edge-preserving
capability but do not perform well in smoothing Gaussian noise.
Next, we modify the filters so that they perform all three image
enhancement tasks. These filters are based on the idea that
individual pixels should not be uniformly fired by each of the fuzzy
rules. To demonstrate the capability of our filtering approach,
it was tested on several different image enhancement problems.
These experimental results demonstrate the speed, filtering
quality, and image sharpening ability of the new filter.
INTRODUCTION
NOISE smoothing and image enhancement are conflicting
objectives in most image processing applications. The
objectives of image enhancement are to remove impulsive
noise, to smooth nonimpulsive noise, and to enhance edges or
other salient structures in the input image. Noise filtering can
be viewed as replacing the gray-level value of every pixel in
the image with a new value depending on the local context.
Ideally, the filtering algorithm should vary from pixel to pixel
based on the local context. For example, if the local region
is relatively smooth, then the new value of the pixel can be
determined by averaging neighboring pixel values. On the
other hand, if the local region contains edges or impulse noise
pixels, a different type of filtering should be used. However,
it is extremely hard, if not impossible, to set the conditions
under which a certain filter should be selected, since the local
conditions can be evaluated only vaguely in some portions of
an image. Therefore, a filtering system needs to be capable of
reasoning with vague and uncertain information; this suggests
the use of fuzzy logic.
PREVIOUS FUZZY-BASED WORK
Because fuzzy set theory has the potential capability to
efficiently represent input/output relationships of dynamic
systems, this theory has gained popularity, especially in pattern
recognition and computer vision applications [5]–[8]. In these
areas there have been many efforts to develop fuzzy filters
for signal/image processing, with promising results [9]–[12].
In the well-known rule-based approach for image processing
[13], one may use human knowledge expressed heuristically
in linguistic terms. This approach is highly nonlinear in nature
and cannot be easily characterized by traditional mathematical
modeling. However, this approach allows us to incorporate
heuristic fuzzy rules into conventional methods, leading to a
more flexible design technique. For instance, in [14] Yang and
Tou applied heuristic fuzzy rules to improve the performance
of the traditional multilevel median filter.
EXPERIMENTAL RESULTS
As mentioned above, the FCF has potential for edge preserva-
tion. To verify this property, we need to quantitatively evaluate
the quality of filtering. The mean-square-error (MSE) between
the edges of the original image and those of the image after fil-
tering will be used as a measure of the edge preserving ability.
We use the acronym MSEE to indicate this criterion. In the se-
quel we will perform some experiments to illustrate the perfor-
mance of the FCF.
CONCLUSION
In this paper we presented three new filtering methods based
on the use of fuzzy logic control. The goal of the filtering
process was to simultaneously satisfy the three tasks of image
enhancement: edge preservation, impulsive noise removal, and
smoothing of nonimpulsive noise. The first proposed filter
(the FCF) was only successful in performing the first two
tasks. It was modified (the SFCF) to improve its ability to
smooth Gaussian noise. We then performed several different
experiments to demonstrate its effectiveness. The performance
of the SFCF on several different types of images was compared
with the performance of a number of well-known filters.