04-08-2014, 03:47 PM
Image Segmentation Based on Watershed and Edge Detection Techniques
[attachment=66581]
Abstract
A combination of K-means, watershed segmentation method, and Difference In Strength (DIS) map was used to
perform image segmentation and edge detection tasks. We obtained an initial segmentation based on K-means clustering
technique. Starting from this, we used two techniques; the first is watershed technique with new merging procedures based on
mean intensity value to segment the image regions and to detect their boundaries. The second is edge strength technique to
obtain an accurate edge maps of our images without using watershed method. In this paper: We solved the problem of
undesirable oversegmentation results produced by the watershed algorithm, when used directly with raw data images. Also,
the edge maps we obtained have no broken lines on entire image and the final edge detection result is one closed boundary per
actual region in the image.
Introduction
Any gray tone image can be considered as a
topographic surface. If we flood this surface from its
minima and, if we prevent the merging of the waters
coming from different sources, we partition the image
into two different sets: The catchment basins and the
watershed lines. If we apply the watershed
transformation to the image gradient, the catchment
basins should theoretically correspond to the
homogeneous gray level regions of this image.
However, in practice, this transform produces an
important over-segmentation due to noise or local
irregularities in the gradient image
Gradient Calculations
In contrast to a classical area based segmentation, the
watershed transform [8] was executed on the gradient
image. The gradient defined the first partial derivative
of an image and contains a measurement for the change
of gray levels. The gradient values (G (x, y)) of the
initial segmented image were obtained using firstly the
approximation of the gradient operator [1] in x, y
directions (equation (4)) as two 3x3 masks.
Watershed Algorithm and Processing Procedures
Because the regions in the image characterized by
small variations in gray levels have small gradient
values, Thus in practice, we often see watershed
segmentation applied to gradient of an image, rather
than to the image itself. The aim of the watershed
transform is to search for regions of high intensity
gradients (watersheds) that divide neighbored local
minima (basins). For applying the watershed transform
an advanced, fast, and an accurate algorithm proposed
by Vincent [8] was used. From this algorithm: A
marker image included zero marker values of
watershed line pixels was obtained. Then in our work:
1. We used 3x3 mask to scan this marker image to find
these zero marker values, turn them to their
intensity values as in original image and compared
these values with their neighbor pixels intensity to
assign them to one marker region. We did that
because discontinuity in the watershed pixels
happened by using this algorithm. We deleted all
watershed pixels (zero marker values) to obtain
second marker image represents the markers of
image regions only.
Difference in Strength Technique
The DIS for each pixel was calculated using equation
(7) [10]. After processing all the input pixels, the DIS
map was obtained. In DIS map, the larger the DIS
value is, the more the pixel is likely located at the
edge. At this step, a 3x3 window runs pixel by pixel on
the input image. When the window runs over the
bolder of the input image, pixels outside the bolder are
given the gray level of the input nearest to it. The DIS
Conclusion
In our proposed method, the segmentation regions and
their boundaries were defined well and all of the
boundaries are accurately located at the true edge as
shown clearly from Figure3-(c, d), Figure 5-g, and
Figure 6-c. And if we take k-means first and then DIS
with 25% of mean DIS, we will get all the edges of our
images as shown in the Figure 6 above, so we don't
need to use watershed technique.
Also, we concluded that using multi-threshold
which is important to eliminate false edges and thus
obtain larger regions, the DIS map consists of all edge
information about the input image even on the smooth
regions, and the combination of k-means, watershed
segmentation method, DIS map are good techniques to
perform image segmentation and edge detection tasks,
where the final segmentation results are one closed
boundary per actual region of the image under study,
and the two edge strengths gradient values (T1, T2), T1
is less than T2, are very sensitive to get good results.
Where the incorrect choice of these values gives us
uncorrected image segmentation and edge detection
results and this is a disadvantage. So we will develop
this work in future with automatically determined the
threshold values