Advanced
A Study on Edge Detection using Directional Mask in Impulse Noise Image
A Study on Edge Detection using Directional Mask in Impulse Noise Image
Journal of the Korea Institute of Information and Communication Engineering. 2014. Dec, 18(12): 2982-2988
  • Published : December 31, 2014
Download
PDF
Export by style
Article
Author
Metrics
Cited by
About the Authors
Lee, Chang-Young
Kim, Nam-Ho

Abstract
The edge detection is a pre-processing of such as image segmentation, image recognition, etc, and many related studies are being conducted both in domestic and abroad. Representative edge detection methods are Sobel, Prewitt, Laplacian, Roberts and Canny edge detectors. Such existing methods are possible for superb detections of edges if edges are detected from videos without noises. However, for video degraded by the salt-and-pepper noise, the edge detection characteristic is shown to be insufficient due to the noise influence. Therefore, in this study, the area is separated as the top, down, left and right from the mask's center pixel first to acquire a superb edge detection characteristic from the video damaged by the salt-and-pepper noise. And the algorithm that detects the final edge by applying the directional mask on the assumed factor of mask that is obtained according to the result of determination for the noise status of representative pixel value of each area.
Keywords
View Fulltext