Leaf disease detection: Datasets & Models
Computer vision that detects and localizes diseased regions on plant leaves from field or greenhouse images. Identifies symptoms like spots, blight, and rust so growers can act before damage spreads.
Leaf disease detection
This leaf disease detection workflow takes field or greenhouse images of crop foliage and runs an object detection model to locate diseased regions on individual leaves. It draws bounding boxes around symptoms such as leaf spots, blight, rust, mildew, and lesions, then labels each detection by symptom type so growers can respond before damage spreads.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate leaf disease detection
Manual crop scouting for leaf disease is slow, subjective, and hard to scale across large acreage, and early symptoms are easily missed until an outbreak is already underway. Automating detection with computer vision lets teams monitor thousands of plants consistently, catch infections early, and target fungicide applications only where they're needed instead of blanket spraying. In agriculture, that translates to reduced crop loss, lower chemical costs, and faster, data-backed decisions during critical growth windows.
Key benefits
An RF-DETR detection model delivers accurate localization of disease symptoms even against cluttered foliage backgrounds, and integrates with existing drone, greenhouse, and mobile camera setups you already have. It scales from a single field trial to farm-wide monitoring, and detections can feed directly into scouting reports, spray maps, and yield-protection dashboards. You get repeatable, objective assessments that don't depend on the availability of an expert agronomist.
How to use it
- Upload an image: Drop any photo into the widget above to try leaf disease detection for free, right on this page.
- Preview instant results: The model detects leaf spot, fungal lesion, leaf blight, powdery mildew, rust pustule, healthy leaf 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 RF-DETR 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 leaf disease detection
RF-DETR is state of the art for real-time object detection, instance segmentation, and keypoint detection, with higher accuracy and lower latency than comparable models, and it's Apache 2.0 licensed. When you're ready to build a production model for leaf disease detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Leaf Disease Detection project to Roboflow Agent.