tailieunhanh - Edge detection algorithm for color images using logical operations

This paper is about a algorithm used for edge detection using logical operations. First image is converted into binary image and then it is rotated left, right, up and down. Afterwards logical AND operation is performed between rotated and original image and results are stored in different variables. | ISSN:2249-5789 Kiran Jot Singh et al, International Journal of Computer Science & Communication Networks,Vol 2(1), 83-86 Edge Detection Algorithm for Color Images using Logical Operations Kiran Jot Singh1, Monika Aggarwal2 Student1, Assistant Professor2 BGIET, Sangrur, Punjab, India Abstract This paper is about a algorithm used for edge detection using logical operations. First image is converted into binary image and then it is rotated left, right, up and down. Afterwards logical AND operation is performed between rotated and original image and results are stored in different variables. After that XOR operation is performed between the results that are stored and then OR operation is performed on all results obtained after XOR operation. These operations are repeated for different values of threshold to get the final result constituting of only edges of that image. This method gives better or comparable output as given by other edge detection algorithms. This algorithm can be applied to variety of colored images. 1. Introduction Edge detection is a procedure of finding significant changes in a image. Edge detection is basically the points where sharp changes in brightness occur typically from the border between different objects [1]. Edges characterize object boundaries and therefore useful for segmentation, registration, and identification of objects in scenes [2]. Many edge detectors are used these days but canny edge detection algorithm gives best output as compared to other edge detection algorithms such as Sobel, Prewitt and Robert [3]. Canny’s edge detection algorithm is more complex then these algorithms and uses two threshold vales. So its computational expenses are more. According to study done by Carol L. Novak and Steven A. Shafer [4] 90% of the edges are about the same in gray level and in color images. It implies that 10% of the edges are left over in gray level images. Since color images give more