Abstract
Trials of a computer vision machine (The CatchMeter) for identifying and measuring different species of fish are described. The fish are transported along a conveyor underneath a digital camera. Image processing algorithms: determine the orientation of the fish utilising a moment-invariant method, identify whether the fish is a flatfish or roundfish with 100% accuracy, measure the length with a standard deviation of 1.2 mm and species with up to 99.8% sorting reliability for seven species of fish. The potential application of the system onboard both research and commercial ships is described. The machine can theoretically process up to 30,000 fish/h using a single conveyor based system.
Original language | English |
---|---|
Pages (from-to) | 203-210 |
Number of pages | 8 |
Journal | Fisheries Research |
Volume | 80 |
Issue number | 2-3 |
DOIs | |
Publication status | Published - Sept 2006 |
Bibliographical note
The Authors would like to thank Jan-Tore Øvredal and Bjørn Totland of the Institute of Marine Research in Bergen for their help and comments regarding this work and also for arranging the test cruises on the Norwegian G. O. Sars research vessel. Erik Andersen of Matcon in Denmark for his advice regarding the mechanical systems of the CatchMeter. The companies and institutions that funded this work: The Norwegian Research Council, The Norwegian Fishery Research Fund, The Nordic Council of Ministers, The Institute of Marine Research in Bergen and Scantrol.Keywords
- Computer vision
- Fish
- Fish species
- Image processing
- Sorting