StomataCounter: a deep learning method applied to automatic stomatal identification and counting

Abstract

O_LIStomata 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.\nC_LIO_LIWe 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.\nC_LIO_LIOur network achieves 98.1% identification accuracy on Ginkgo SEM micrographs, and 94.2% transfer accuracy when tested on untrained species.\nC_LIO_LITo facilitate adoption of the method, we make a web tool available under http://www.stomata.science/\nC_LI

Plant phenotyping relevance

気孔という植物形質の画像ベース自動同定・計数法を開発し、異なる画像・種で精度検証した研究であり、方法自体が中心です。

Code and data availability

保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。