A Novel Edge Detection Filter by Using Firefly Algorithm

Edge detection is a signal processing algorithm common in artificial intelligence and image recognition problems. An edge is the boundary between an object and thebackground, and indicates the boundary between overlapping objects. There are a lot of algorithms in the literature for enhancing and detecting edges. The reason for this is that edgesform the outline of an object. In this paper, we proposed a new edge detection filter (3*3 mask) for grey level image edgedetection by using the firefly algorithm. The Firefly algorithm has some characteristics that make it suitable for solvingoptimization problem, like higher converging speed and less computation rate. In the proposed method, we use a single image and its edge map by using firefly algorithm to find anedge detection filter. The proposed segmentation method, is employed for four benchmark images and the performancesobtained outperform results obtained with well-known methods, like ’canny’, ‘sobel’,’Log’ and ‘prewitt’. To evaluate theproposed method we use peak signal to noise ratio method (PSNR) and root-mean-square error (eRMS).

Keywords:

Edge detection , Edge detection filter , Firefly algorithm , Grey level image