khornlund/severstal-steel-defect-detection

Kaggle Segmentation Challenge

40
/ 100
Emerging

This project helps steel manufacturing engineers automatically identify and classify surface defects on steel sheets using images. It takes raw images of steel surfaces as input and outputs segmented images that highlight and label different types of defects. Quality control and operations managers in steel production plants would use this to improve efficiency and maintain high product quality.

263 stars. No commits in the last 6 months.

Use this if you need to quickly and accurately detect common surface defects like 'patches', 'pitted surface', 'scrathes', and 'rolled-in scale' on steel during manufacturing.

Not ideal if you need to detect highly unusual or very subtle defects that are not well-represented in existing training data, or if you require real-time, ultra-low-latency detection on a production line without any post-processing.

steel-manufacturing quality-control defect-detection industrial-inspection operations-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

263

Forks

58

Language

Jupyter Notebook

License

Last pushed

Oct 07, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/khornlund/severstal-steel-defect-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.