Fish Recognition Optimization in Various Backgrounds Using Landmarking Technique and YOLOv4

Abstract

The identification and categorization of fish is a popular and fascinating research topic. Many researchers have developed expertise in fish detection, both underwater and outside the water, which is particularly beneficial for population management and aquaculture. This paper proposes a fish recognition approach using the landmarking methodology with YOLO version 4 to identify and categorize fish with different backdrop circumstances. The approach can be used both underwater and on land. The proposed approach was evaluated using four distinct types of fish from the BYU dataset. The final test result determined that the accuracy reached 96.60%, with an average classification score of 99.67% at the 60% threshold. The result is 4.94 % better than the most frequent traditional labelling approach.