Determination of volume of alaska pollock (Theragra chalcogramma) by image analysis


Creative Commons License

BALABAN M. O., CHOMBEAU M., GÜMÜŞ B., CIRBAN D.

Journal of Aquatic Food Product Technology, vol.20, no.1, pp.45-52, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 20 Issue: 1
  • Publication Date: 2011
  • Doi Number: 10.1080/10498850.2010.531996
  • Journal Name: Journal of Aquatic Food Product Technology
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.45-52
  • Keywords: image analysis, volume prediction, Alaska pollock, cubic splines, WEIGHT, FISH
  • Akdeniz University Affiliated: Yes

Abstract

The objective of this study was to develop two methods to predict the volume of whole Alaska pollock and to compare the results with the experimentally measured volumes. One hundred fifty-five whole pollock, obtained from a Kodiak processor, were individually immersed in a graduated cylinder equipped with an outflow tube to catch the displaced water as a result of immersion. The weight of the water was recorded. Then the fish were placed in a light box equipped with a digital video camera, and the side view and top view recorded (2 images for each fish). A reference square of known surface area was placed by the fish. A cubic spline method to predict volume by integration of cross-sectional area slices based on the top and side views and an empirical equation using dimensional (length L, width W, depth D) measurements at three locations of the fish image were developed. The R2 value for the correlation between the L × W × D versus measured volume was 0.987. The best R2 for the correlation of the predicted volume by the cubic spline method versus the measured volume was 0.99. Image analysis can be used reliably to predict the volume of whole Alaska pollock. © Taylor & Francis Group, LLC.