LuigiFederico/PatchCore-for-Industrial-Anomaly-Detection

PatchCore method for Industrial Anomaly Detection + CLIP

26
/ 100
Experimental

This project helps quality control and operations engineers in manufacturing identify defective parts on production lines. It takes images of normally functioning parts as input during training and then, when presented with new parts, outputs whether a part is defective and highlights the specific area of the defect. This is particularly useful for visual inspection tasks where only examples of 'good' products are readily available.

No commits in the last 6 months.

Use this if you need to automate defect detection in industrial manufacturing when you primarily have access to images of non-defective items for training.

Not ideal if you need a solution for anomaly detection in non-image data or if you have a balanced dataset of both defective and non-defective parts for training.

manufacturing quality control visual inspection production line automation defect detection industrial imaging
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

42

Forks

4

Language

Python

License

Last pushed

Aug 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LuigiFederico/PatchCore-for-Industrial-Anomaly-Detection"

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