nick-leland/DistortionML

A machine learning model that will determine if a photo has any visual manipulation (bulge, pinch, skew, spiral, etc) and then attempts to revert them.

14
/ 100
Experimental

This tool helps you analyze images to detect if they have been visually altered with effects like bulges, pinches, or spirals. You input a potentially distorted image, and the system first identifies if distortion is present, then attempts to reverse it, providing a clearer, unmanipulated version. This is useful for anyone who needs to verify the authenticity of visual evidence or restore damaged image content.

No commits in the last 6 months.

Use this if you need to automatically identify and correct visual distortions in images, such as those used to obscure details or manipulate content.

Not ideal if you are looking for advanced image editing features beyond distortion detection and reversal, or if your images contain complex artistic filters rather than basic geometric distortions.

image-authenticity forensic-analysis photo-restoration content-verification
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

21

Forks

Language

Jupyter Notebook

License

Last pushed

Aug 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nick-leland/DistortionML"

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