A tank fish recognition and tracking system using computer vision techniques

Aquarium usually provides the visitors with pictures and some description of the fishes in the exhibition tank. In this paper, an intelligent fish recognition system using computer vision is proposed to help aquarium to educate people about the fishes in the tank. The designed system provides a convenient and friendly interface to help the users to retrieve the related fish information they are interested. The system includes three sub-systems: (1) fish object detection system (2) fish object tracking system (3) fish object recognition system. Two types of fish indexing system (offline and real time) have been designed and implemented.