A COMPARATIVE STUDY OF THE EFFICIENCY OF LAYERS' COLOR SPACES ON EDGE DETECTION METHODS

摘要

Edge detection is of a major interest in digital image processing and computer vision and forms the basic stage in the process of pattern recognition and image segmentation. It is important to select the most suitable edge detection method in terms of color space and the best layer in each color space to identify the contents of the image. In this paper, a comparative study was conducted on the effect of color space layers on the efficiency of edge detection methods. Six color systems: RGB, HSL (Hue, Saturation, Lightness) and HSV (Hue, Saturation, Value), YUV, La b and Ycbcr [21] were tested and decomposed into their layers. Five edge detection methods were applied: Sobel, Prewitt, Laplace, Canny and Robert, to each layer of color spaces, each chromatic space was examined separately to determine the best layer most suitable for each edge detection method. The results showed differences between the layers of each color space, and between the color spaces for the edges detection methods.