12-09-2013, 02:16 PM
IMAGE SEGMENTATION BY USING EDGE DETECTION
IMAGE SEGMENTATION.pdf (Size: 483.83 KB / Downloads: 60)
Abstract
In this paper, we present methods for edge
segmentation of satellite images; we used seven techniques
for this category; Sobel operator technique, Prewitt
technique, Kiresh technique, Laplacian technique, Canny
technique, Roberts technique and Edge Maximization
Technique (EMT) and they are compared with one another
so as to choose the best technique for edge detection
segment image. These techniques applied on one satellite
images to choose base guesses for segmentation or edge
detection image.
INTRODUCTION
Edge detection is a fundamental tool used in most image
processing applications to obtain information from the
frames as a precursor step to feature extraction and object
segmentation. This process detects outlines of an object and
boundaries between objects and the background in the
image. An edge-detection filter can also be used to improve
the appearance of blurred image; to this cause more studies
take this subject can be give some of these studies briefly:
Soft computing techniques have found wide applications.
One of the most important applications is edge detection for
image segmentation. The process of partitioning a digital
image into multiple regions or sets of pixels is called image
segmentation. Edge is a boundary between two
homogeneous regions. Edge detection refers to the process
of identifying and locating sharp discontinuities in an
image. In this paper, the main aim is to survey the theory of
edge detection for image segmentation using soft computing
approach based on the Fuzzy logic, Genetic Algorithm and
Neural Network[1].The Canny algorithm uses an optimal
edge detector based on a set of criteria which include
finding the most edges by minimizing the error rate,
marking edges as closely as possible to the actual edges to
maximize localization, and marking edges only once when a
single edge exists for minimal response[2].The non-
maximal suppression stage identifies pixels that are local
maxima in the direction of the gradient using the magnitude
and orientation of the pixels.
Roberts Cross Edge Detector
The Roberts Cross operator performs a simple, quick to
compute, 2-D spatial gradient measurement on an image. It
thus highlights regions of high spatial frequency which
often correspond to edges. In its most common usage, the
input to the operator is a grayscale image, as is the output.
Pixel values at each point in the output represent the
estimated absolute magnitude of the spatial gradient of the
input image at that point.
Edge Maximization Technique (EMT)
In images when there is more than one homogenous region
(e.g. an image has many objects with different gray levels)
or where there is a change on illumination between the
objects and its background. In this case, portion of the
objects may be merged with the background or portions of
the background may appear as an object.
Form the above fact, any of the automatic threshold
selection techniques performance becomes much better in
images with large homogenous separated regions.
These conditions are fully satisfied for edge-enhanced
image where most of the areas are homogenous (including
the areas inside the objects plus the areas inside the
background), and also having a well separated with areas
that fall between the objects and the background (edges).
This improve technique make use of the previous idea and
works on edge-enhanced image.
CONCLUSION
In this paper, the comparative studies applied by using
seven techniques of edge detection segment: Sobel, Roberts,
Canny, Laplacian, Kirsh, and Edge Maximum Technique
(EMT) on the Saturn original image Figure.1.A comparative
study are explained & experiments are carried out for
different techniques Kiresh, EMT and Perwitt techniques
respectively are the best techniques for edge detection this
result can be seen in the Figure.2.