Page 47 -

CHAPTER
2

Edge-Detection Techniques

2.1 The Purpose of Edge Detection

Edge detection is one of the most commonly used operations in image analysis,
and there are probably more algorithms in the literature for enhancing and
detecting edges than any other single subject. The reason for this is that edges
form the outline of an object, in the generic sense. Objects are subjects of interest
in image analysis and vision systems. An edge is the boundary between an
object and the background, and indicates the boundary between overlap-
ping objects. This means that if the edges in an image can be identified
accurately, all the objects can be located, and basic properties such as area,
perimeter, and shape can be measured. Since computer vision involves the
identification and classification of objects in an image, edge detection is an
essential tool.
Figure 2.1 illustrates a straightforward example of edge detection. There are
two overlapping objects in the original picture: (a), which has a uniform grey
background; and (b), the edge-enhanced version of the same image has dark
lines outlining the three objects. Note that there is no way to tell which parts
of the image are background and which are object; only the boundaries between
the regions are identified. However, given that the blobs in the image are the
regions, it can be determined that the blob numbered ‘‘3’’ covers up a part of
blob ‘‘2’’ and is therefore closer to the camera.
Edge detection is part of a process called segmentation — the identification
of regions within an image. The regions that may be objects in Figure 2.1 have
been isolated, and further processing may determine what kind of object each

21