Categorizing cells in phytoplankton images

Authors:
Adas Gelzinis;Antanas Verikas;Marija Bacauskiene;Irina Olenina;Sergej Olenin
Affiliations:
Department Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania;Department Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania and Intelligent Systems Laboratory, Halmstad University, Halmstad, Sweden;Department Electrical & Control Equipment, Kaunas University of Technology, Kaunas, Lithuania;Department of Marine Research, Environmental Protection Agency, Klaipeda, Lithuania and Coastal Research and Planning Institute, Klaipeda University, Klaipeda, Lithuania;Coastal Research and Planning Institute, Klaipeda University, Klaipeda, Lithuania
Venue:
GAVTASC'11 Proceedings of the 11th WSEAS international conference on Signal processing, computational geometry and artificial vision, and Proceedings of the 11th WSEAS international conference on Systems theory and scientific computation
Year:
2011

Citing 6
Cited 0

Random Forests

Machine Learning
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
Automatic In Situ Identification of Plankton

WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Selecting salient features for classification based on neural network committees

Pattern Recognition Letters
Mining data with random forests: A survey and results of new tests

Pattern Recognition
Screening web breaks in a pressroom by soft computing

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article is concerned with detection of invasive species--Prorocentrum minimum (P. minimum)--in phytoplankton images. The species is known to cause harmful blooms in many estuarine and coastal environments. A new technique, combining phase congruency-based detection of circular objects in images, stochastic optimization, image segmentation, and SVM and random forest-based classification of objects was developed to solve the task. The developed algorithms were tested using 114 images of 1280 × 960 pixels. There were 2088 P. minimum cells in the images in total. The algorithms were able to detect 93.25% of objects representing P. minimum cells and correctly classify 94.9% of all objects. The results are rather encouraging and will be used to develop an automated system for obtaining abundance estimates of the species.