taikiinoue45/PaDiM

PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization

31
/ 100
Emerging

This tool helps quality control inspectors and manufacturing engineers automatically detect defects and irregularities in products using images. You feed it a collection of images of good products, and it learns what's normal. Then, for new products, it highlights any unusual areas in the image, helping you quickly identify flaws like scratches, cracks, or missing parts. It's designed for someone overseeing product quality on an assembly line.

No commits in the last 6 months.

Use this if you need to automate visual inspection for manufacturing defects and localize exactly where the anomalies occur in product images.

Not ideal if your anomaly detection needs go beyond visual inspection or if you require real-time, high-speed inference without GPU resources.

quality-control manufacturing-inspection defect-detection visual-qa industrial-automation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

39

Forks

3

Language

Python

License

MIT

Last pushed

Jun 02, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/taikiinoue45/PaDiM"

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