Towards fish individuality-based aquaculture

• Published in: IEEE Transactions on Industrial Informatics
• Main Authors: Schraml, R., Hofbauer, H., Jalilian, E., Bekkozhayeva, D., Saberioon, M., Cisar, P., Uhl, A.
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2021
• Subjects: Atlantic salmon
• Online Access: https://gfzpublic.gfz-potsdam.de/pubman/item/item_5002614; https://gfzpublic.gfz-potsdam.de/pubman/item/item_5002614_4/component/file_5006111/5002614.pdf

By bringing concepts of precision farming to intensive aquaculturem fish production can be optimized to be more sustainable while focusing on fish welfare criteria. This means to shift from mass to smart production which requires to consider each fish as an individual instead of viewing on the total stock of fish. Therefore it is required to be able to identify each fish in a tank or sea cage. In this paper, we prove the feasibility of fish identification using the iris as biometric characteristic. For this purpose, a new database was captured which enables us to consider the basic feasibility as well as to prove the permanence of the iris pattern of Atlantic salmon in terms of ageing. Results show that the iris pattern of Atlantic salmon is suited for biometric identification, but the pattern changes significantly in short periods.