Feasibility of automating otolith ageing using CT scanning and machine learning / B.R. Moore, J. Maclaren, C. Peat, M. Anjomrouz, P.L. Horn, S. Hoyle.
By: Moore, B. R.
Contributor(s): McLaren, J | Peat, C | Anjomrouz, M | Horn, P. L. (Peter L.)
| Hoyle, S | Fisheries New Zealand (Government agency) [issuing body.].
Material type: 
BookSeries: New Zealand fisheries assessment report: 2019/58Publisher: Wellington, New Zealand : Fisheries New Zealand, Tini a Tangaroa, 2019.Description: 1 online resource.ISBN: 9781990008665.Holdings: ELECTRONIC Online resources: FAR 2019/58 Fisheries Infosite | NIWA document server | National Digital Heritage Archive Open Access Summary: 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.
| Item type | Current location | Call number | Copy number | Status | Date due | Barcode |
|---|---|---|---|---|---|---|
PDF
|
WELLINGTON ONLINE | ELECTRONIC | 1 | Not for loan | 395720 |
"October 2019."
Archived by the National Library of New Zealand in PDF.
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.
ELECTRONIC
There are no comments on this title.