Underwater Shrimp Digital Image Segmentation Using Edge Detection Method on Fog Network

Abstract

This study takes the theme of underwater shrimp digital image segmentation using edge detection methods on fog networks, the problem raised in this study is to compare the accuracy of the shrimp digital image segmentation process using five edge detection methods, the parameters used are PSNR and MSE values, five methods Edge detection used in the digital image segmentation process of underwater shrimp is the Canny, Sobel, Prewitt, Roberts and Laplacian of Gaussian (LOG). This study proposes a fog network technique in the computing process by taking data through an underwater camera connected to a fog server to provide real-time information services, the study was carried out using 5 digital images of underwater shrimp extracted from video data, namely image frames to 140, 850, 1185, 5950 and 6390 which are implemented in 5 edge detection methods. From the results of the study, the best edge detection method was the canny method with the lowest PSNR accuracy rate of 4.4619 dB and the highest MSE value of 106.65.