Build with RF-DETR
Build a Foreign Object Detection App Free with RF-DETR
Catch plastic, hair, paper, and other contaminants in food before it ships and get a pass or fail result. Label images, train RF-DETR free, and deploy it as a workflow.
- No credit card
- No ML team required
- Edge, on-prem or API
Build a Foreign Object Detection App with Roboflow’s Free RF-DETR
In short
A foreign object detection app uses computer vision to inspect food on a processing or packing line and find contaminants that do not belong, like plastic, hair, or paper, then fails any product where one is found. The model to train for it is RF-DETR, Roboflow's open-source real-time detection model. With Roboflow you label your images, train RF-DETR for free, and deploy it as a workflow that returns an annotated image, a count of foreign objects, and a PASS or FAIL result.
How it works
The workflow behind the foreign object detection app
Use this Foreign Object Detection with RF-DETR workflow: each image goes to an RF-DETR model that finds contaminants in the food, then through a confidence filter and into two tracks. One counts the foreign objects and turns the count into PASS or FAIL, the other draws boxes and labels, and both meet where the verdict is written onto the image. Every block is editable in the low-code builder, and the Roboflow Agent can build it from a description.
- output_image
- inspection_result
- foreign_object_count
- predictions
How to build a foreign object detection app with RF-DETR
Open the workflow and add your images
Click "Use this free template" to copy the workflow into your Roboflow workspace. Upload images of your product on the line taken with the camera and lighting you will use, including clean product and examples of each contaminant you need to catch.
Label contaminants and train RF-DETR
Use Auto Label to box each foreign object, then review and correct the results, paying close attention to small or low-contrast items. Train an RF-DETR model and select it in the detect_foreign_objects block. RF-DETR fine-tunes well on small custom datasets, so you can start with the examples you have.
Tune the threshold and the pass/fail rule
Set the threshold in filter_by_confidence so real contaminants are caught without flagging normal food texture. Add classes for specific contaminants if you need a separate count for each.
Deploy and connect it to your line
Deploy the workflow as a Serverless Cloud API, or on your own hardware through Inference. Each run returns output_image, inspection_result, foreign_object_count, and predictions for your reject system or quality records.
Roboflow MCP
Build it from your AI assistant with the Roboflow MCP
Connect the Roboflow MCP Server to Claude, Cursor, or any MCP-compatible assistant and build the whole foreign object detection app in natural language, without leaving your editor.
Ask an assistant like Codex or ChatGPT to search Roboflow Universe for food contamination datasets, upload and auto-label your line images, and train an RF-DETR model to find foreign objects. It can then create and run the foreign object detection workflow on test images and deploy it to your devices.
Paste it into your coding agent and it walks you through the rest. Setting up by hand? The server is https://mcp.roboflow.com/mcp.
Open the Roboflow listing, select Connect, then sign in to Roboflow. Available on desktop, web and mobile.
Run these commands in your terminal, then sign in to Roboflow. Claude Code CLI has no documented browser install link.
Opens the Roboflow plugin listing. Sign in if prompted and confirm the install on Cursor to add MCP and skills.
Opens the Roboflow plugin listing. Install the plugin and sign in to Roboflow when prompted to connect your account.
Opens the Roboflow plugin listing shared by ChatGPT and Codex. Install the plugin and sign in to Roboflow when prompted to connect your account.
Then run /mcp auth roboflow in Gemini CLI to sign in. Gemini CLI has no documented browser install link.
What your foreign object detection app can do
Trained on your images, an RF-DETR model handles the specific, hard-to-catch cases that matter on your line:
- Spot small fragments of plastic, paper, or packaging in food
- Find hair and thin fibers that blend into the product
- Catch contaminants that are similar in color to the food
- Tell foreign objects apart from normal food texture and crumbs
- Inspect every item at line speed, not a sample
- Flag contaminated product before it is packed and shipped
Want to customize your foreign object detection app?
Describe the foreign object detection app you want in plain English: your product, the contaminants you need to catch, and what should happen when one is found. The Roboflow Agent finds the data, trains an RF-DETR model, and assembles the workflow for you.
Open source
Roboflow’s RF-DETR is open source, Apache-2.0, and free to use
RF-DETR is an open-source, Apache-2.0 licensed real-time object detection model developed by Roboflow. The rfdetr Python package and most RF-DETR models are free to use, including in commercial products, and you can train and run everything on your own hardware. No account or lock-in required.
Apache-2.0 and free
The rfdetr package, Nano to Large detection, every segmentation size and Keypoint are Apache-2.0 licensed and free to use, including commercially.
Install and train locally
pip install rfdetr on Python 3.10+. Fine-tune on your own data in a few lines and run it entirely on your machine.
State of the art on COCO
RF-DETR is a real-time detector that is SOTA on COCO. RF-DETR-Large reaches 56.5 AP at 6.8 ms on an NVIDIA T4, and uses a DINOv2 backbone.
Deploy anywhere
Export to ONNX or TensorRT and run on GPU, CPU, or NVIDIA Jetson at the edge, or serve it through the Roboflow hosted API.
| Models | Licence |
|---|---|
| Detection: Nano, Small, Medium, Large | Apache-2.0 |
| Segmentation: every size, Nano to 2XLarge | Apache-2.0 |
| Keypoint (preview) | Apache-2.0 |
| Detection: Atto, Femto, Pico, XL, 2XL (rfdetr[plus]) | PML 1.0: commercial use included on Roboflow; commercial self-hosting needs the Enterprise add-on |
RF-DETR vs. other free detectors
A foreign object detection app has to find small, unpredictable contaminants in food on a moving line, often close in color to the product, so the model needs to be both accurate and fast. Here is how RF-DETR, fine-tuned on your own product images, compares for real-time inspection.
| Model | Tasks | Best for | License |
|---|---|---|---|
| RF-DETR | Detection, segmentation (keypoints in preview) | Real-time detection you fine-tune on your own data, one model across tasks | Apache-2.0 (Nano to Large, all segmentation); PML 1.0 (Atto, Femto, Pico, XL, 2XL) |
| D-FINE | Detection | Precision localization when you do not need to fine-tune | Apache-2.0 |
| YOLO | Detection, segmentation, pose | Fast CNN-based detection with a large ecosystem | AGPL-3.0 (commercial license required for closed-source use) |
| GroundingDINO | Open-vocabulary detection | Finding objects by text prompt with no training, not real-time | Apache-2.0 |
| SAM 2 / SAM 3 | Segmentation | Pixel-precise masks; SAM 3 adds text-prompted segmentation | Apache-2.0 (SAM 2), SAM License (SAM 3) |
| Florence-2 | Vision-language | Reading, captioning, and OCR on images | MIT |
The takeaway for this app: RF-DETR runs in real time, so it can inspect every item as it passes. It fine-tunes well on small custom datasets and is open source, so you can train on your own products and contaminants and run the model wherever you need it.
Build your foreign object detection app free today
Label, train, and deploy your foreign object detection app in one place.