Automated Counting of Zebrafish: An Image Processing Approach

• Ehsan Noshahr ^[1] ; Cristiano V. M. Araujo ^[2] ; Alvaro Rodriguez ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
  2. [2] Instituto de Ciencias del Mar

     Instituto de Ciencias del Mar

     Barcelona, España

     
• Localización: Proceedings XoveTIC 2025: Impulsando el talento científico / coord. por Manuel Lagos Rodríguez, Hilda Romero-Velo, Álvaro Leitao , Javier Pereira-Loureiro , Manuel Penedo , 2026, ISBN 978-84-9749-925-5, págs. 199-206
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Accurate quantification of fish populations is a critical task in aquaculture and behav-ioral research. In this work, we present a lightweight image processing pipeline for the automaticcounting of zebrafish (Danio rerio) in a multi-compartment aquatic system. The approach com-bines background subtraction, morphological refinement, and watershed segmentation to esti-mate fish counts directly from raw video without annotated training data. The method enablesnon-invasive and reproducible counting while remaining computationally efficient and inter-pretable. Although challenges remain under occlusion and limited visibility, the method reducesreliance on manual observation and demonstrates that classical image-processing techniques canprovide efficient, interpretable, and accessible solutions for early-stage behavioral experiments.