EDGE detection technique has been used in variety of
image processing applications include extracting the
edges from image and typically is utilized before object
segmentation and feature extraction [1].
Edges are recognized by abrupt intensity variations in an
image. The first gradient is typically calculated to locate the
edges. The 3 x 3 masks are used to extract the edges from
image, and convolved them through it. Prewitt, Canny and
Sobel algorithms have been commonly used for edge
detection purposes with different masks.
Perwitt edge detection technique is selected due to
efficiency and simplicity in the single mask. Figure 1 shows
typical Perwitt edge detection masks. In this technique, the
edges are detected by convolving horizontal and vertical
masks Gx and Gy respectively, through the image. The masks
are orthogonal to each other and use to measure the
difference among the adjacent pixels gray level in horizontal
and vertical direction.