Lights, camera, pliman! An R package for plant image analysis

Abstract Manual measurements of quantitative traits are time consuming and error prone. Therefore, high‐throughput phenotyping methods that allow a rapid and accurate assessment are vital to a growing range of researchers such as agronomists, breeders, phytopathologists, geneticists, ecologists and biologists. Here, I describe the pliman R package, a collection of functions designed (but not limited) to conduct plant image analysis. The package will help researchers to (a) manipulate, segment and compute image indexes based on Red, Green, Blue, Red‐Edge and Near‐Infrared bands; (b) measure leaf area and shape; (c) quantify plant disease severity; (d) count and extract features (e.g. area, perimeter, radius, circularity and eccentricity) of objects such as grains, leaves, pods, pollen and cells; and (e) compute RGB indexes for each object in an image. In this paper, I describe the main features implemented in the package, guiding the user along a gentle learning curve with practical and reproducible examples. The results of validation studies implemented to count objects in different scenarios (combination of seed sizes, background colour and image resolution), measure leaf area, and quantify plant disease severity have shown that pliman measurements are highly concordant with existing ‘gold standard’ tools. The pliman package offers a flexible, intuitive and richly documented working environment for image‐based phenotyping, being an interesting alternative to free and commercial ‘point‐and‐click’ solutions. R users will find the package fairly easy to use and will be surprised at how the setting of a few arguments will allow processing thousands of images while they enjoy a cup of coffee.