Try it out!
WHO WE ARE
We’re a team of marine scientists,
programmers and machine learning experts,
working together to advance AI in Fisheries Science.
Our Story
An online tool for estimating fish age from otolith images using Deep Learning.
For more details, see:
DeepOtolith: A web-tool for fish age estimation from otolith images using deep learning (Documentation).Sample otolith/scale images and the source code can be found here
Motive
Accurate estimation of fish ageing is crucial for assessing the status of fish stocks and developing management plans for ensuring their sustainability. The prevailing methods of fish ageing are based on manual readings of otolith images by experts, a process that is often time-consuming and costly.
Future Work
Our long term aim is to extend this tool by adding more fish species and improving the predictability of existing ones.
Contributing
DeepOtolith welcomes collaborations with researchers who want to contribute towards the automation of fish ageing.
References
- Ordoñez A. et al. 2020. Explaining decision of deep neural networks used for fish age prediction. PLoS ONE 15(6), e0235013.
- Politikos D. et al. 2021. Automating fish age estimation combining otolith images and deep learning: the role of multitask learning. Fisheries Science 242, 106033.
- Vabø R. et al. 2020. Automatic interpretation of salmon scales using deep learning. Ecological Informatics 63, 101322.
Other
- The design and implementation was developed in Python language with Flask.
- We declare that images are not stored neither are sent to third parties.
Contributors
- Web development: Nikos Sikiniotis, Pavlos Dedousis, Dimitris Politikos
- Web release: Dimitris Politikos, George Petasis, Michail Iordanis
- AI methods: Dimitris Politikos, George Petasis, Alba Ordoñez, Rune Vabø, Arnt-Børre Salberg, Elde Moen, Ketil Malde
- Dataset & Interpretation: Archontia Chatzispyrou, Katerina Anastasopoulou, Chryssi Mytilineou
Contact Us
If you have any questions, suggestions or interested in testing your case study, please contact Dr. Dimitris Politikos
dimpolithcmr.gr
