dennishnf/unsupervised-anomaly-detection

This repository describes the implementation of an unsupervised anomaly detector using the Anomalib library.

39
/ 100
Emerging

This tool helps quality control inspectors identify defective items on a production line by analyzing images. You provide a set of images of 'normal', defect-free products, and it learns to spot unusual patterns. The output is an indication of which new products deviate from the norm, helping you catch manufacturing flaws quickly. It's designed for someone managing or working in industrial quality assurance.

No commits in the last 6 months.

Use this if you need to automatically detect visual anomalies or defects in manufactured goods, particularly on items like metal parts, without manually setting rules for what constitutes a 'defect'.

Not ideal if your anomalies are subtle, non-visual, or if you have very little data for what 'normal' looks like.

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

How are scores calculated?

Stars

28

Forks

7

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 06, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dennishnf/unsupervised-anomaly-detection"

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