Titre du document / Document title

Automated measurement of species and length of fish by computer vision

Auteur(s) / Author(s)

WHITE D. J. ⁽¹⁾ ; SVELLINGEN C. ⁽²⁾ ; STRACHAN N. J. C. ⁽¹⁾ ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

⁽¹⁾ University of Aberdeen, Cruickshank Building, Aberdeen AB24 3UU, ROYAUME-UNI
⁽²⁾ Scantrol, Sandviksboder Ic, Bergen 5035, NORVEGE

Résumé / 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.

Revue / Journal Title

Fisheries research   ISSN 0165-7836   CODEN FISRDJ 

Source / Source

2006, vol. 80, n^o2-3, pp. 203-210 [8 page(s) (article)] (14 ref.)

Langue / Language

Anglais

Editeur / Publisher

Elsevier, Amsterdam, PAYS-BAS  (1981) (Revue)

Mots-clés anglais / English Keywords

Vertebrata ; Fishery ; Image processing ; Computer vision ; Pisces ;

Mots-clés français / French Keywords

Vertebrata ; Pêcherie ; Traitement image ; Vision ordinateur ; Pisces ;

Mots-clés espagnols / Spanish Keywords

Vertebrata ; Pesquería ; Procesamiento imagen ; Visión ordenador ; Pisces ;

Mots-clés d'auteur / Author Keywords

Computer vision ; Image processing ; Fish ; Fish species ; Sorting ;

Localisation / Location

INIST-CNRS, Cote INIST : 19360, 35400014234083.0090