Mask detection: Datasets & Models
Face mask detection identifies whether people in a scene are wearing a mask, and flags uncovered or improperly worn faces. It runs on standard camera feeds to automate compliance monitoring in real time.
Mask detection
This face mask detection workflow processes images or video frames from standard camera feeds and locates each person's face, drawing a bounding box around it. It then classifies every detected face as masked or unmasked, flagging cases where a mask is missing or improperly worn.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate mask detection
Manual mask compliance checks require a staff member to watch entrances or monitor camera walls continuously, which does not scale across multiple sites and is prone to fatigue and inconsistency. Automating face mask detection with computer vision lets a single model watch every camera at once, log violations, and trigger alerts the moment an uncovered face enters a monitored zone. For security and surveillance teams, this removes the labor of stationing personnel at checkpoints and creates an auditable record of compliance. It also frees human operators to respond to genuine incidents rather than routine policy enforcement.
Key benefits
Teams get consistent, around-the-clock monitoring that plugs directly into existing IP and CCTV camera streams without new hardware. The detection model scales from a single door to a full multi-camera deployment, and RF-DETR delivers accurate real-time detection even in crowded scenes with partial occlusion. Detected events can feed dashboards, alerts, or access-control systems for immediate action.
How to use it
- Upload an image: Drop any photo into the widget above to try mask detection for free, right on this page.
- Preview instant results: The model detects mask, face, person, head 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 mask 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 mask detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Mask Detection project to Roboflow Agent.