FISH RECOGNITION OF UNDERWATER VIDEO BY USING REAL TIME IMAGE PROCESSING AT KELONG PENARAK HABITATS

Abstract

A fish image recognition system is proposed in this project to recognize the fish in underwater video taken by remote operated vehicle at Kelong Penarak, Langkawi. It is a computer vision application for automatically differentiating the species of fish from the input digital images into the system. The system to be developed is for fish types sorting at Kelong Penarak at Langkawi, Malaysia for the study of the fish species there to be done for SIRIM, ROVTEK and Fishermen Community at Penarak, whereby the fish species chosen are totally seawater types. An algorithm will be developed based on shapes and recognition by using Matlab. The photographs taken on target fish species and it will be stored in .mat file as database. The fish image recognition system designed will be able to differentiate the selected features of fish which are the shapes of the fish species. A Graphical User Interface (GUI) will be designed to represent the recognized fish species. The details of the fish is also stated in the result.