FISH DISEASE DETECTION USING IMAGE BASED MACHINE LEARNING TECHNIQUE IN AQUACULTURE

In tank farming, fish infections pose a serious threat to the safety of the food source. It is still hard to spot sick fish in aquaculture at an early stage due to a lack of appropriate infrastructure. To halt the spread of disease, it is critical to spot diseased fish as soon as possible. Our objective in this study is to learn more about the salmon fish sickness because salmon aquaculture accounts for 70% (2.5 million lots) of the market and is the fastest-growing food manufacturing system globally. Fish that have been exposed to various viruses can be identified with the aid of an artificial intelligence tool and excellent picture processing. This task consists of two separate components. In the main portion, noise reduction and picture enhancement have been associated with photo pre-processing and segmentation, respectively. After deleting the implicated features in the second phase, we classify the diseases using the machine learning Support Vector Machine (SVM) technique using a kernel function. The processed photos from the first section have been run through this (SVM) model. After that, we balance a thorough test of the suggested approach combination using the collection of salmon fish photographs used to evaluate the condition of the fish. The dataset used for this work is entirely fresh and includes and does not include photo enhancement. Based on the results, it has been determined that our SVM performs admirably with 91.42 and also 94.12 percent accuracy, respectively, with and without improvement