Expert and machine discrimination of marine flora: a comparison of recognition accuracy of field-collected phytoplankton

The categorisation of labelling of phytoplankton specimens is carried out manually using microscopes by marine ecologists and taxonomists. Research to automate the task has been on going for many years. Although many systems have been shown to work in small-scale laboratory conditions with cultured populations, few have succeeded when applied to field collected specimens. The reasons are diverse, but are principally due to severely degraded performance of the chosen processing algorithms in the presence of noise and natural morphological variability of the organisms. The application of statistical and neural network pattern learning methods have allowed progress to be made in this difficult area. The machine learning system DiCANN was trained on 128 of the 310 image data set and tested on the 182 samples. This study has highlighted the difficulties facing human ecologists and has shown that automation methods can perform as well as humans on complex categorisations.

[1]  Manfred Rolke,et al.  Size structure analysis of zooplankton samples by means of an automated image analyzing system , 1984 .

[2]  S. González-Gil,et al.  A procedure to estimate okadaic acid in whole dinoflagellate cells using immunological techniques , 1995, Journal of Applied Phycology.

[3]  Phil F. Culverhouse,et al.  Committees, collectives and individuals: Expert visual classification by neural network , 1997, Neural Computing & Applications.

[4]  J. Álvarez-Borrego,et al.  Diffraction pattern applicability in the identification of Ceratium species , 1999 .

[5]  R R Sokal,et al.  Classification: Purposes, Principles, Progress, Prospects , 1974, Science.

[6]  A. Solow,et al.  Estimating the taxonomic composition of a sample when individuals are classified with error , 2001 .

[7]  L Boddy,et al.  Pattern recognition in flow cytometry. , 2001, Cytometry.

[8]  J. Álvarez-Borrego,et al.  Optical–digital system applied to the identification of five phytoplankton species , 1998 .

[9]  S. Lek,et al.  The use of artificial neural networks to predict the presence of small‐bodied fish in a river , 1997 .

[10]  F. Colijn,et al.  Phytoplankton monitoring by flow cytometry , 1994 .

[11]  A. D. Poularikas,et al.  Automated sizing, counting and identification of zooplankton by pattern recognition , 1984 .

[12]  Loic Le Dean,et al.  Application of a digital pattern recognition system to Dinophysis acuminata and D. sacculus complexes , 1996 .

[13]  Phil F. Culverhouse,et al.  Biological pattern recognition by neural networks , 1991 .

[14]  B. Reguera,et al.  Phased cell division and other biological observations in field populations of Dinophysis spp during cell cycle studies , 1996 .

[15]  P. Truquet,et al.  Morphological Study of Atypical Dinophysis acuta Ehrenberg from Chilean Coastal Waters by a Digital Pattern - Recognition System , 1998 .

[16]  W. K. Stewart,et al.  Rapid visualization of plankton abundance and taxonomic composition using the Video Plankton Recorder , 1996 .

[17]  Euan S. Harvey,et al.  A Comparison of the Accuracy and Precision of Measurements from Single and Stereo-Video Systems , 2002 .