Detection and Classification of Fishes using Enhancement and Restoration Techniques
Abstract
The problem statement of our article is to enhance the quality of the image as it helps in the inspection of infrastructure and helps in marine biology and research and the main objective of our article is to enhance the images so we undertook some efficient techniques like image enhancement and restoration techniques to improve the quality of the image and we have implemented fish detection and classification methodologies. Next coming to fish detection techniques we have used a the-nature-conservancy-fisheries-monitoring dataset from the Kaggle which has nearly 1000 images to test and train and dataset and detect the fishes from the image, coming to fish classification techniques we have seven classes of fishes.
KEYWORDS: Dark channel Prior, Canny edge Detection, Bilateral filtering, KNN, Multiclass classification.