Anisotropic diffusion based edge detector for detecting coral reefs edges

This paper presents a new edge detection method to efficiently detect coral reefs edges. The new edge detection method is based on an anisotropic diffusion where it is used to produce minimum image noise disturbances without reducing the significant edge information and at the same time preserving salient edges. The proposed method has been compared with other established edge detection methods such as Sobel, Prewitt, Roberts, LoG and Canny edge detectors under various noisy environments. The coral reefs images obtained at 3 meters depth were used in this study. The performance of the proposed method is compared with other established methods using visual inspection as well as parametric measure, i.e. Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). The experimental results show that the proposed method outperformed other established edge detection methods in both aspects.