© 2004 by ICES/CIEM International Council for the Exploration of the Sea/Conseil International pour l'Exploration de la Mer
Enumeration, measurement, and identification of net zooplankton samples using the ZOOSCAN digital imaging system
a Laboratoire d'écologie numérique, Université de Mons-Hainaut Avenue Maistriau, 19, B-7000 Mons, Belgium
b Laboratoire d'Océanographie de Villefranche (UMR 7093), Station Zoologique, Observatoire Océanologique BP 28, F-06234 Villefranche sur mer Cedex, France
*Correspondence to P. Grosjean: tel: +32 65 37 34 97; fax: +32 65 37 33 12. e-mail: philippe.grosjean{at}umh.ac.be.
Identifying and counting zooplankton are labour-intensive and time-consuming processes that are still performed manually. However, a new system, known as ZOOSCAN, has been designed for counting zooplankton net samples. We describe image-processing and the results of (semi)-automatic identification of taxa with various machine-learning methods. Each scan contains between 1500 and 2000 individuals <0.5 mm. We used two training sets of about 1000 objects each divided into 8 (simplified) and 29 groups (detailed), respectively. The new discriminant vector forest algorithm, which is one of the most efficient methods, discriminates between the organisms in the detailed training set with an accuracy of 75% at a speed of 2000 items per second. A supplementary algorithm tags objects that the method classified with low accuracy (suspect items), such that they could be checked by taxonomists. This complementary and interactive semi-automatic process combines both computer speed and the ability to detect variations in proportions and grey levels with the human skills to discriminate animals on the basis of small details, such as presence/absence or number of appendages. After this checking process, total accuracy increases to between 80% and 85%. We discuss the potential of the system as a standard for identification, enumeration, and size frequency distribution of net-collected zooplankton.
Keywords: image analysis, long-term series, machine-learning, net samples, pattern recognition, size spectrum, zooplankton
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  A. Gislason and T. Silva Comparison between automated analysis of zooplankton using ZooImage and traditional methodology J. Plankton Res., December 1, 2009; 31(12): 1505 - 1516. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
L. Zarauz, X. Irigoien, and J. A. Fernandes Changes in plankton size structure and composition, during the generation of a phytoplankton bloom, in the central Cantabrian sea J. Plankton Res., February 1, 2009; 31(2): 193 - 207. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
X. Irigoien, J. A. Fernandes, P. Grosjean, K. Denis, A. Albaina, and M. Santos Spring zooplankton distribution in the Bay of Biscay from 1998 to 2006 in relation with anchovy recruitment J. Plankton Res., January 1, 2009; 31(1): 1 - 17. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
J. A. Fernandes, X. Irigoien, G. Boyra, J. A. Lozano, and I. Inza Optimizing the number of classes in automated zooplankton classification J. Plankton Res., January 1, 2009; 31(1): 19 - 29. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
J. L. Bell and R. R. Hopcroft Assessment of ZooImage as a tool for the classification of zooplankton J. Plankton Res., December 1, 2008; 30(12): 1351 - 1367. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
L. Zarauz, X. Irigoien, and J. A. Fernandes Modelling the influence of abiotic and biotic factors on plankton distribution in the Bay of Biscay, during three consecutive years (2004-06) J. Plankton Res., August 1, 2008; 30(8): 857 - 872. [Abstract] [Full Text] [PDF]
|
|