that the accuracy of our automated aperture measurements was equivalent to that of manual measurements, however had higher sensitivity (i,e., lower false negative rate ) and the process speed was at least 80 times faster. The outstanding performance of our proposed method for automating a laborious and repetitive task will allow researchers to focus on deciphering complex phenomena.To fully understand the molecular mechanisms underlying the regulation of stomatal movement, sufficient numbers of stomata must be analysed under a range of experimental conditions. To date, ocular . CC-BY-NC 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/365098 doi: bioRxiv preprint first posted online Jul. 9, 2018;. CC-BY-NC 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/365098 doi: bioRxiv preprint first posted online Jul. 9, 2018;. CC-BY-NC 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/365098 doi: bioRxiv preprint first posted online Jul. 9, 2018; DeepStomata 2 micrometer-assisted visual estimation has been widely used to measure stomatal apertures; however, as stomatal movements are highly sensitive to their environment, the number of stomata that can be analysed before their apertures change is very limited using this method. Imaging intact or replica leaf surfaces enables the analysis to be deferred, alleviating the possibility of aperture changes during observation; however, aperture measurements are still labour intensive. Recent technical advances in computer vision can assist the quantification process. CARTA, an ImageJ plugin that utilizes a self-organizing map algorithm, allowed the semi-automatic classification of open/closed-state stomata 4 . More recently, a script that automatically quantifies stomatal apertures has been developed (https://github.com/TeamMacLean/stomatameasurer); however, it requires that images be taken using a confocal scanning laser microscope with a high-contrast background. In many studies, images are acquired using an optical camera with bright-field microscopy, which contains dense and complex pixel information. To the best of our knowledge, no methods currently facilitate the automatic measurement of stomatal apertures from such images.As a solution to these issues, phenotypes that can serve as a proxy for stomatal opening have been used to identify factors that regulate stomatal movement. Thermal imaging of leaves or monitoring their water loss can reflect the stomatal aperture-dependent transpiration rat...