Pre-trained models and learning set for classification of Southern North Sea plankton images collected by the Plankton Imager (Pi-10)
Abstract
The pre-trained Plankton Imager (Pi-10) Convolutional Neural Network (CNN) models provide a ready-to-use deep learning solution for automated zooplankton image classification. Built upon the FlowCam phytoplankton classifier developed by VLIZ within the iMagine project, the Pi-10 pre-trained models efficiently recognize and categorize planktonic organisms from Pi-10 images, with a focus on the Southern North Sea.The current datasets holds the model ‘Anasimyia’
Fields of Study & Subjects
Advanced Neural Network Applications
Cell Image Analysis Techniques
Domain Adaptation and Few-Shot Learning
Publication details
- Journal / source
- Flanders Marine Institute (Flanders Marine Institute)
- Publication date
- 1 January 2026
- Language
- EN
- Document type
- Dataset