Academic Editor: Youssef EL FOUTAYENI
Received |
Accepted |
Published |
29 January 2020 |
13 February 2020 |
10 March 2020 |
Abstract: The edge detection is an important procedure in the image processing. It is a main tool used for pattern recognition, image segmentation and scene analysis. The main function of edge detection is to locate and identify sharp discontinuities in images. These discontinuities are due to abrupt changes in pixel intensities which characterizes boundaries of objects in a scene. These boundaries are used to recognize objects present in a scene, to differentiate areas of the image, to segment images, to extract information often reduced relevant to characterize the image, or to reconstruct objects in three dimensions. In this paper, we present an approach aimed at improving edge detection in images, particularly by Sobel, Prewitt, Roberts and Canny edge detectors. The proposed improvement is based on the quadtree decomposition of the image into zones with common characteristics. The proposed approach allowed to display more edges compared to those displayed when the detectors are applied to the entire image.
