Identification of Baikal phytoplankton inferred from computer vision methods and machine learning


  • Lysenko, A. V. 1, 2
  • Oznobikhin, M. S. 1, 2
  • Kireev, E. A. 1, 2
  • Dubrova, K. S. 1
  • Vorobyeva, S. S. 1
  • 1 Limnological Institute, Siberian Branch of the Russian Academy of Sciences, Ulan-Batorskaya str., 3, Irkutsk, 664033, Russia
    2 Institute of Mathematics and Information Technologies, Irkutsk State University, Gagarina str., 20, Irkutsk, 664003, Russia



phytoplankton classification, machine learning, transfer learning, image processing, computer vision


This study discusses the problem of phytoplankton classification using computer vision methods and convolutional neural networks. We created a system for automatic object recognition consisting of two parts: analysis and primary processing of phytoplankton images and development of the neural network based on the obtained information about the images. We developed software that can detect particular objects in images from a light microscope. We trained a convolutional neural network in transfer learning and determined optimal parameters of this neural network and the optimal size of using dataset. To increase accuracy for these groups of classes, we created three neural networks with the same structure. The obtained accuracy in the classification of Baikal phytoplankton by these neural networks was up to 80%.