This tutorial shows basic steps for analyzing an RGB image of a single plant. Many more options are available at each step, if needed. Some of these are illustrated in the tutorial: Single Plant RGB Image Workflow

This tutorial will teach you how to utilize tools to select Region(s) of Interest (ROIs). There are different methods for selecting areas that contain objects of interest.

This tutorial will teach you how to utilize tools to threshold (or segment) an object from the background.

This tutorial will teach you how to input and output images and data.

This tutorial will teach you how to use a color card to perform color correction on an image.

This tutorial will teach you how to analyze images of multiple objects in an image. This may be leaves (shown in this example), seeds, or other non-plant objects that are not attached to each other. Traits extracted include shape, color, and number of objects.

This tutorial will teach you how to calibrate cameras. This is useful for controlling distortion for cameras with a fish-eye type lens or other lens distortion.

Learn how to analyze a tray of Arabidopsis plants for size, shape, and color.

Learn about the watershed function, which can be used to roughly segment individual leaves. In this case, the number of objects reported from the analyze watershed function is a rough estimation of the number of leaves. The Watershed Segmentation Function is a PlantCV function based on code contributed by Suxing Liu, Arkansas State University.

Learn to analyze plant morphology, such as leaf angle, number of leaves, internode length, and more, depending on the plant species and imaging settings.

Learn how to analyze pictures of seeds, including size, shape, and color. This tutorial works on all seed types, so long as the seeds are a different color from the background.

An introduction to analyzing VIS (RGB) images of single plants (or single objects) with PlantCV.

For dual VIS/NIR workflows, an RGB image is used to create a mask for the plant and then extract data from the NIR image.

This tutorial introduces the K-Means Clustering algorithm. This is useful for classifying difficult to segment images. The example here is a seed, but could be used for plants and disease, as well.

This tutorial introduces the naive bayes machine learning algorithm. This is useful for classifying difficult to segment images, for example, classifying disease in leaves.

This tutorial will teach you how to analyze images captured with a speciality camera, such as the CropReporter from Phenovation used in this tutorial. Traits extracted include NPQ, Fv/Fm, chlorophyll index, anthocyanin index, and plant shape.

This tutorial will teach you how to analyze images captured with a speciality camera, such as the CropReporter from Phenovation used in this tutorial. This tutorial is for multiple objects (such as more than one plant or leaf) in an image. Traits extracted include NPQ, Fv/Fm, chlorophyll index, anthocyanin index, and plant shape.

This workflow is published with Duenwald et. al (2025) JoVE and describes how to analyze a single plant, RGB image in a photo studio.