Fish Disease Detection System: A Case Study of Freshwater Fishes of Bangladesh

Abstract

The proposed system is designed for automatic detection and classification of fish diseases in freshwater especially Rangamati Kaptai Lake and Sunamganj Hoar area of Bangladesh. Our experimental result is indicating that the proposed approach is significantly an accurate and automatic detection and recognition of fish diseases. This study presents fish disease detection based on the K-means and C-means fuzzy logic clustering method to segment the filtering image. Gabor's Filters and Gray Level Co-occurrence Matrix (GLCM) are used to extracts the features from the segmented regions. Finally Multi-Support Vector Machine (M-SVMs) is used for classification of the test image. The proposed system demonstrated a comparison between K-means clustering and C-means fuzzy logic. The proposed methodology gave 96.48% accuracy using K-means and 97.90% using C-means fuzzy logic which is the highest accuracy rate to compare other existing methods. The proposed system has been experimented in the MATLAB environment on infected fish images of Rangamati Kaptai Lake and Sumangan Hoar area. It is a challenging task of fisheries farming in Hoar areas and Lake areas to detect fish diseases initially. The proposed methodology can detect and classify different fish diseases in early stages and also contributes to improved results for fish disease detection.

Cutting‐edge technologies for detecting and controlling fish diseases: Current status, outlook, and challenges

“…In addition, Duan et al created a web‐based tele‐diagnostic system (T‐Vet) for conducting online diagnosis (synchronous) and offline diagnosis (asynchronous) that allows farmers to provide multimedia information such as photos, graphics, and text as the input (Sikder et al, 2021). This system's knowledge base was built on more than 300 rules and 400 photos and graphics, which can detect 126 different forms of illnesses in nine different species of common freshwater fish.…”

Exploring opportunities of Artificial Intelligence in aquaculture to meet increasing food demand

“… S. No Disease diagnosis Technique/tool Detection Accuracy Reference Fish parasites (Ichthyophthirius multifiliis, Gyrodactylus kobayashii, and Argulus japonicus) Deep learning algorithm YOLOv4 through python 95.41 % Li et al, 2023 Difference between Infected fish and fresh fish Support Vector Machine (SVM) algorithm 91.42 % without augmentation 94.12 % with augmentation Ahmed et al, 2022 , Ahmed et al, 2022 WSSV (White Spot Syndrome Virus Artificial Neural network, Fuzzy Algorithm 90 % Fabregas et al, 2018 EUS (Epizootic Ulcerative Syndrome) Machine learning algorithims Principal Component Analysis (PCA) and Histogram of Oriented Gra-dients (HOG) 86 % Malik et al, 2017 EUS (Epizootic Ulcerative Syndrome) Principal Component Analysis (PCA) and K-menas Algorithm 90 % Chakravorty et al, 2015 Red Spot and White spot Convolutional Neural Network (CNN) 91.67 % for white spot 94.44 % for red spot Hassan et al 2022 EUS, Red Spot, Argulus, Tail and Fin Rot, Broken antennae rostrum and Bacterial Gill rot. C-means Fuzzy logic and K-means clustering 96.48 % for K-means clustering 97.90 % for C-means Fuzzy logic Sikder et al, 2021 …”