denguir/student-teacher-anomaly-detection

Student–Teacher Anomaly Detection with Discriminative Latent Embeddings

40
/ 100
Emerging

This project helps quality control engineers automatically identify defects or anomalies in industrial products by analyzing images. You provide a dataset of normal, anomaly-free product images, and it outputs anomaly maps that highlight defective regions in new images. It's used by manufacturing and quality assurance professionals to detect flaws on a production line.

185 stars. No commits in the last 6 months.

Use this if you need to automatically spot surface defects or manufacturing anomalies on products using computer vision, especially when you primarily have images of 'good' products.

Not ideal if your anomalies are not visually detectable or if you lack a sufficient dataset of normal, defect-free images for training.

quality-control manufacturing defect-detection industrial-inspection visual-inspection
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

185

Forks

46

Language

Python

License

Last pushed

Nov 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/denguir/student-teacher-anomaly-detection"

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