High-quality pollen is a prerequisite for plant reproductive success. Pollen viability and sterility can be routinely assessed using common stains and manual microscope examination, but with low overall statistical power. Current automated methods are primarily directed towards the analysis of pollen sterility, and high throughput solutions for both pollen viability and sterility evaluation are needed that will be consistent with emerging biotechnological strategies for crop improvement. Our goal is to refine established labelling procedures for pollen, based on the combination of fluorescein (FDA) and propidium iodide (PI), and to develop automated solutions for accurately assessing pollen grain images and classifying them for quality. We used open-source software programs (CellProfiler, CellProfiler Analyst, Fiji and R) for analysis of images collected from 10 pollen taxa labelled using FDA/PI. After correcting for image background noise, pollen grain images were examined for quality employing thresholding and segmentation. Supervised and unsupervised classification of per-object features was employed for the identification of viable, dead and sterile pollen. The combination of FDA and PI dyes was able to differentiate between viable, dead and sterile pollen in all the analysed taxa. Automated image analysis and classification significantly increased the statistical power of the pollen viability assay, identifying more than 75,000 pollen grains with high accuracy (R2 = 0.99) when compared to classical manual counting. Overall, we provide a comprehensive set of methodologies as baseline for the automated assessment of pollen viability using fluorescence microscopy, which can be combined with manual and mechanized imaging systems in fundamental and applied research on plant biology. We also supply the complete set of pollen images (the FDA/PI pollen dataset) to the scientific community for future research.