Automated image analysis- and soft computing-based detection of the invasive dinoflagellate Prorocentrum minimum (Pavillard) Schiller

  • Authors:

  • A. Verikas;A. Gelzinis;M. Bacauskiene;I. Olenina;S. Olenin;E. Vaiciukynas

  • Affiliations:

  • Department of Electrical & Control Equipment, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania and Intelligent Systems Laboratory, Halmstad University, Box 823, S-30118 Ha ...;Department of Electrical & Control Equipment, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania;Department of Electrical & Control Equipment, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania;Department of Marine Research, Environmental Protection Agency, Taikos str., 26, LT-91144, Klaipeda, Lithuania and Coastal Research and Planning Institute, Klaipeda University, H. Manto 84, LT-922 ...;Coastal Research and Planning Institute, Klaipeda University, H. Manto 84, LT-92294, Klaipeda, Lithuania;Department of Electrical & Control Equipment, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2012

Quantified Score

Hi-index 12.05

Visualization

Abstract

A long term goal of this work is an automated system for image analysis- and soft computing-based detection, recognition, and derivation of quantitative concentration estimates of different phytoplankton species using a simple imaging system. This article is limited, however, to detection of objects in phytoplankton images, especially objects representing one invasive species-Prorocentrum minimum (P. minimum), which is known to cause harmful blooms in many estuarine and coastal environments. A new technique, combining phase congruency-based detection of circular objects, stochastic optimization, and image segmentation was developed for solving the task. The developed algorithms were tested using 114 images of 1280x960 pixels size recorded by a colour camera. There were 2088 objects representing P. minimum cells in the images in total. The algorithms were able to detect 93.25% of the objects. Bearing in mind simplicity of the imaging system used the result is rather encouraging and may be applied for future development of the algorithms aimed at automated classification of objects into classes representing different phytoplankton species.