Statistical filtering to aid in the classification of phytoplankton: The effects of image library size and phytoplankton shape

The demand for image classification methods has increased due to technological advancements that enable more intensive phytoplankton monitoring. Regardless of whether the methods are based on statistical or machine learning algorithms, algal taxa may be misidentified in taxonomically diverse samples, in which phytoplankton morphology and image traits can be variable. We evaluated the statistical filtering performance for two approaches to image library development, which we applied independently to seven commonly occurring algal shapes. To do so, we used the statistical filter in the image processing software of an imaging flow cytometer (FlowCAM) and previously classified samples. One statistical filtering approach used a small selection of images (5-15 images of a target taxon) from the same sample being filtered (i.e., intrinsic), and the other used a larger selection of images (30-80 images of a target taxon) compiled from different samples. Filter accuracy, precision, and recall va..., , # Statistical filtering to aid in the classification of phytoplankton: The effects of image library size and phytoplankton shape

Dataset DOI: 10.5061/dryad.prr4xgz0f

## Description of the data and file structure

Images for phytoplankton samples collected from the nearshore of Nottawasaga Bay, Lake Huron in 2015 were collected using a FlowCAM vs-4 (Yokagawa Fluid Imaging Technologies, Inc.) imaging flow cytometer, ran in trigger mode using the 10X objective. We statistically filtered the phytoplankton image dataset using the built-in \"like selected particles (statistical)\" functions of VisualSpreadsheet software (versions 3.4.5 and 5.9.074, Yokagawa Fluid Imaging Technologies, Inc.). Data in the provided Data-from-Farrow-Ackerman-Statistical-Filtering.xlsx file correspond to the raw statistical filtering outputs for the compiled library method and the intrinsic library method, which are necessary for the calculation of the following performance metrics: accuracy, precision, and recall..., ,