RT Journal Article SR Electronic T1 StomataCounter: a deep learning method applied to automatic stomatal identification and counting JF bioRxiv FD Cold Spring Harbor Laboratory SP 327494 DO 10.1101/327494 A1 Karl C. Fetter A1 Sven Eberhardt A1 Rich S. Barclay A1 Scott Wing A1 Stephen R. Keller YR 2018 UL http://biorxiv.org/content/early/2018/05/21/327494.abstract AB Stomata fulfill an important physiological role and are often phenotyped by researchers in many fields. Currently, no fully automated method exists to perform this task. Researchers typically rely on manual counts of stomata, which is an error-prone method and difficult to reproduce.We introduce StomataCounter, an automated stomata counting system using a deep convolutional neural network to identify pores in a variety of different microscopic images. We used a human-in-the-loop approach to train and refine a neural network on a large variety of microscopic images, which helps us achieve robust detection among a number of datasets.Our network achieves 98.1% identification accuracy on Ginkgo SEM micrographs, and 94.2% transfer accuracy when tested on untrained species.To facilitate adoption of the method, we make a web tool available under http://www.stomata.science/