Prediction fat percentage and visceral weight from whole fish images with a multi-input neural network

Y. Xue*, J.W.M. Bastiaansen, H. Komen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademic

Abstract

In aquaculture, high accuracy in trait measurements benefits the genetic progress from a breeding program. Breeding traits like fat percentage and visceral weight are related to feed/cost efficiency of growth and product quality, and important metabolism and health indicators. Problems concentrate on finding the proper methods to accurately measure or predict these traits, as most current approaches are invasive, labour-intensive or may disturb or damage the fish. Interior trait prediction from image analysis would allow a real-time, large-scale and non-invasive alternative for such traits. This study investigates using whole-fish images in combination with exterior traits to improve the prediction of fillet fat percentage and visceral weight. The result of including images as extra input shows improvement on the accuracy of fat percentage prediction. The neural network extracted contour-based features and brings into view several biological indicators that appear to be informative for prediction.
Original languageEnglish
Title of host publicationProceedings of 12th World Congress on Genetics Applied to Livestock Production (WCGALP)
Subtitle of host publicationTechnical and species orientated innovations in animal breeding, and contribution of genetics to solving societal challenges
EditorsR.F. Veerkamp, Y. de Haas
Place of PublicationWageningen
PublisherWageningen Academic Publishers
Pages590-593
ISBN (Electronic)9789086869404
DOIs
Publication statusPublished - 2022
EventWorld Congress on Genetics Applied to Livestock Production: WCGALP 2022 - Rotterdam, Netherlands
Duration: 3 Jul 20228 Jul 2022

Conference/symposium

Conference/symposiumWorld Congress on Genetics Applied to Livestock Production: WCGALP 2022
Country/TerritoryNetherlands
CityRotterdam
Period3/07/228/07/22

Fingerprint

Dive into the research topics of 'Prediction fat percentage and visceral weight from whole fish images with a multi-input neural network'. Together they form a unique fingerprint.

Cite this