Fisheries Infosite

Feasibility of automating otolith ageing using CT scanning and machine learning

Filename
FAR-2019-58-Automating-otolith-ageing.pdf

Link to file
FAR-2019-58-Automating-otolith-ageing.pdf (1.3 MB)

Abstract
 This study explored using CT scanning and machine learning to automate fish ageing. CT scanning resolved banding patterns on the surface of snapper, hoki and ling otoliths, but resolution and contrast were too low to detect outer bands in images through otolith cores. A convolutional neural network was used to estimate snapper and hoki ages from otolith images, and after limited training obtained promising consistency with human ageing. Further development of both techniques is recommended.
 
 


Document date
Monday, 7 October 2019
Document type
V 1.3
File format
Adobe PDF
File size
1.3 MB
Reference number
2019/58
Sort order


Uploaded from
FAR-2019-58-Automating-otolith-ageing.pdf

Uploaded date
Monday, 7 October 2019

Search tags
AUTHOR: Moore, B.R.; Maclaren, J.; Peat, C.; Anjomrouz, M.; Horn, P.L.; Hoyle, S.;
ISBN: 978-1-99-000866-5;
ISSN: 1179-5352;
FAR: 2019/58;

If you are having problems opening this file, you may not have the software on your computer needed to view it. Click the link below to download and install a suitable program.