Precision Disease Diagnosis in Aquaculture Using Aqua Spectra Imaging and Machine Learning

Abstract

Fish diseases present a major challenge to the sustainability and nutritional security of aquaculture. The absence of adequate infrastructure often delays the early detection of diseased  fish, making timely identification of infected seafood essential to prevent widespread illness. This project centers on the diagnosis of diseases affecting salmon, which represents 70% of the aquaculture industry and stands as the fastest-growing food production system worldwide. By leveraging advanced image processing and machine learning techniques, our approach achieves high accuracy in detecting infected fish. The project is divided into two key phases: the first phase focuses on image pre-processing and segmentation to minimize noise and enhance critical features, while the second phase utilizes machine learning algorithms, including Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), to accurately classify the detected diseases. The proposed system aims to enhance disease detection in aquaculture, promoting better health management and boosting overall productivity.