PERBANDINGAN METODE-METODE EDGE DETECTION UNTUK PROSES SEGMENTASI CITRA DIGITAL

Abstract

Edge detection (Edge detection) is executed to detect the operating margins (edges) that restricts two homogeneous image regions with different brightness levels (Pitas, 1993). A digital image edge detection is the process of looking for differences in the intensity of the states boundaries of an object (sub-images) in the entire digital image in question. Purpose of edge detection is to improve the appearance of the boundary line of an area or object in the image. The process of image edge detection is done by looking for the locations of the intensity of the pixels that discontinue with the intensity of the pixels adjacent (neighboring / neighborhood).

There are several methods such as object edge detection operators are known, such as (1) Sobel, (2) Prewitt, (3) Robert, (4) Laplacian of Gaussian, (5) and Canny (6) Kiresh. Each operator has its own advantages and disadvantages in performing edge detection. By doing a combination or in the development of these operators allow to gain a better edge detection (obviously).

One of the contributions of this study for science and technology is the creation of a software application that can be used as a simulation tool using edge detection operators in digital image and its various combinations in order to gain a better edge detection (obviously).

Keywords: Edge detection, detection operator