Plant disease classification: Datasets & Models
Classify crop leaf images into healthy or specific disease categories using a fine-tuned image classification model. Useful for scouting apps, greenhouse monitoring, and precision agriculture pipelines.
Plant disease classification
This workflow accepts a single image of a crop leaf and returns a class label identifying whether the plant is healthy or affected by a specific condition such as early blight, powdery mildew, or bacterial spot. It uses an image classification model trained on a plant disease dataset covering multiple crops and symptom types, making it suitable for scouting apps, greenhouse monitoring, and precision agriculture pipelines.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate plant disease classification
Manual disease scouting depends on trained agronomists walking fields and inspecting plants one by one, which is slow, subjective, and hard to scale across large acreage or many greenhouse benches. A classification model applies consistent judgment to every image, flags likely infections early enough to act, and lets less-experienced field staff capture a photo and get an immediate assessment. For agriculture teams, that means earlier intervention, more targeted spraying, and a documented record of crop health over time.
Key benefits
A ViT-based classifier delivers strong accuracy on fine-grained leaf symptoms and improves as you add labeled examples from your own crops and conditions. It integrates with existing smartphone cameras, drones, and greenhouse imaging hardware, and deploys to the cloud or edge devices for offline field use. Because it runs on standard image inputs, you can scale from a single scouting app to fleet-wide monitoring without changing your capture workflow.
How to use it
- Upload an image: Drop any photo into the widget above to try plant disease classification for free, right on this page.
- Preview instant results: The model detects leaf, tomato leaf, potato leaf, fruit, stem within seconds and returns an annotated image with structured predictions, so you can immediately see how well it works. Adjust the detection classes and re-run until the results fit your scenario.
- Like what you see?: With a free Roboflow account, you can deploy this workflow with the Serverless Cloud API, customize it in your workspace, or train Classification (ViT) on your own images for production accuracy.
- Get started for free: No code or training data required to begin: upload, review the results, and make it part of your stack in a single click.
Recommended model for plant disease classification
When you're ready to build a production model for plant disease classification, we recommend training Classification (ViT). Unlike the ready-to-use model in the demo above, you fine-tune it on your own labeled images for higher accuracy, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Plant Disease Classification project to Roboflow Agent.