KentaItakura/Crack-detection-using-one-class-SVM

This demo shows how to detect the crack images using one-class SVM using MATLAB.

37
/ 100
Emerging

This tool helps engineers and inspectors automatically detect cracks in concrete surfaces using images. You provide a collection of images of concrete, primarily showing normal, uncracked surfaces, and the tool learns what a 'normal' surface looks like. It then processes new images, identifying and flagging those that show cracks, even if it hasn't seen crack images before. This is ideal for quality control in construction or infrastructure maintenance.

No commits in the last 6 months.

Use this if you need to automate the inspection of concrete surfaces for cracks, especially when you have many examples of normal concrete but very few (or no) examples of cracked concrete for training.

Not ideal if you have a balanced dataset with many examples of both normal and cracked concrete, as more traditional classification methods might be more straightforward.

structural-inspection quality-control concrete-maintenance defect-detection image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

18

Forks

4

Language

MATLAB

License

MIT

Last pushed

Oct 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KentaItakura/Crack-detection-using-one-class-SVM"

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