Background: Stomata are tiny pores located on the leaf surface that are central to gas exchange. Stomatal number, size and aperture are key determinants of plant transpiration and photosynthesis, and any variation in these traits can affect plant growth and productivity. Current methods to screen for stomatal phenotypes are tedious, which impedes research on stomatal physiology and hinders efforts to develop resilient crops with optimised stomatal patterning. We developed a rapid non-destructive method to phenotype stomatal traits in four species: wheat, rice, tomato, and Arabidopsis. Results: The method consists of two steps. The first step is to capture images of a leaf surface directly and non-destructively using a handheld microscope, which only takes a few seconds compared to minutes using other methods. This rapid method also provides higher quality images for automated data analysis. The second step is to analyse stomatal features using a machine-learning model that automatically detects, counts stomata and measures size. The accuracy of the machine-learning model in detecting stomata ranged from 89% to 96%, depending on the species. Conclusions: We developed a method that combines rapid non-destructive imaging of leaf surfaces with automated image analysis. The method provides accurate data on stomatal features while significantly reducing time for data acquisition. It can be readily used to phenotype stomata in large populations in the field and in controlled environments.