Fabric defect detection: Datasets & Models
Automated visual inspection that locates and classifies defects in woven, knit, and printed fabrics as they move through production or QC stations. Flags flaws like holes, stains, and broken threads in real time.
Fabric defect detection
This detection workflow locates and classifies fabric defects by drawing bounding boxes around flaws on woven, knit, and printed material as it passes through production or QC stations. It accepts images or video frames from line-scan cameras, area cameras, or inspection light tables and identifies defect types such as holes, oil stains, snags, and broken threads, and it can be trained on a fabric defect dataset to fit your specific materials.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate fabric defect detection
Manual fabric inspection is slow, fatiguing, and inconsistent, inspectors can only examine a fraction of the material at production speeds, and small defects routinely slip through. Automating the check with a detection model lets you scan continuous fabric rolls at line speed, catch flaws early before they propagate into finished goods, and generate a defect map for every meter produced. For manufacturing and QC teams, this reduces costly rework, customer returns, and material waste while creating a traceable record of quality.
Key benefits
An RF-DETR detection model delivers precise defect localization that plugs into existing inspection cameras and PLC-driven reject mechanisms, so you can retrofit lines without new hardware. The approach scales from a single station to multiple lines and improves as you add labeled examples of new defect types. You get consistent, auditable QC coverage across shifts with measurable reductions in escaped defects.
How to use it
- Upload an image: Drop any photo into the widget above to try fabric defect detection for free, right on this page.
- Preview instant results: The model detects hole, stain, broken thread, snag, wrinkle 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 fabric defect 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 fabric defect detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Fabric Defect Detection project to Roboflow Agent.