Quantifying California current plankton samples with efficient machine learning techniques

This paper improves on the accuracy of other published machine learning results for quantifying plankton samples. The contributions of this work are: (1) Clarifying the number of expertly labeled images required for machine learning results. (2) Providing guidance as to what algorithms provide the best performance, and how to tune them. (3) Leveraging an ensemble of models to achieve recall rates beyond any single algorithm. (4) Investigating the applicability of abstaining. (5) Using size fractionation to learn more efficiently. (6) Analysis of efficacy of simple geometric features for plankton identification.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Mark D. Ohman,et al.  A COMPARISON OF ZOOPLANKTON SAMPLING METHODS IN THE CALCOFI TIME SERIES , 1995 .

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Robert J. Olson,et al.  Automated taxonomic classification of phytoplankton sampled with imaging‐in‐flow cytometry , 2007 .

[5]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[6]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[7]  Sandrine Vaz,et al.  Comparison of traditional microscopy and digitized image analysis to identify and delineate pelagic fish egg spatial distribution , 2012 .

[8]  Steven J. Bograd,et al.  CalCOFI: a half century of physical, chemical, and biological research in the California Current System , 2003 .

[9]  L. Bottou,et al.  1 Support Vector Machine Solvers , 2007 .

[10]  Philippe Grosjean,et al.  Enumeration, measurement, and identification of net zooplankton samples using the ZOOSCAN digital imaging system , 2004 .

[11]  Marcel Babin,et al.  Size distribution of particles and zooplankton across the shelf-basin system in southeast Beaufort Sea: combined results from an Underwater Vision Profiler and vertical net tows , 2012 .

[12]  Marc Picheral,et al.  Digital zooplankton image analysis using the ZooScan integrated system , 2010 .