Plankton is the most fundamental component of ocean ecosystems, due to its function at many levels of the oceans food chain. The variations of its distribution are useful indicators for oceanic or climatic events; therefore, the study of plankton distribution is crucial to protect marine ecosystems. Currently, much research is concentrated on the automated recognition of plankton and several imaging-based technologies have been developed for collecting plankton images continuously using underwater image sensors. In this chapter, we propose an automated plankton recognition system, which is based on deep learning methods combined with so-called handcrafted features. The experimental evaluation, carried out on three large publicly-available datasets, demonstrates high classification accuracy of the proposed approach when compared with other classifiers on the same datasets.

Ocean ecosystems plankton classification

Loris Nanni
;
2019

Abstract

Plankton is the most fundamental component of ocean ecosystems, due to its function at many levels of the oceans food chain. The variations of its distribution are useful indicators for oceanic or climatic events; therefore, the study of plankton distribution is crucial to protect marine ecosystems. Currently, much research is concentrated on the automated recognition of plankton and several imaging-based technologies have been developed for collecting plankton images continuously using underwater image sensors. In this chapter, we propose an automated plankton recognition system, which is based on deep learning methods combined with so-called handcrafted features. The experimental evaluation, carried out on three large publicly-available datasets, demonstrates high classification accuracy of the proposed approach when compared with other classifiers on the same datasets.
2019
Recent Advances in Computer Vision - Theories and Applications
978-3-030-02999-9
978-3-030-03000-1
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11577/3308616
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex 73
social impact