ZamDimon/distortion-generator

Neural network for creating distortion while keeping embeddings as close as possible

30
/ 100
Emerging

This tool generates visually distorted versions of original images, while ensuring that the core identity or features of the original image remain detectable by computer vision systems. It takes an image as input and outputs a distorted image. This is useful for researchers and developers working on privacy-preserving computer vision applications or robust image recognition systems.

No commits in the last 6 months.

Use this if you need to anonymize images for privacy reasons but still want them to be recognizable by AI, or to test the robustness of your image recognition models against visual alterations.

Not ideal if you need to create images that are completely unidentifiable by any system, or if you need to generate visually appealing artistic distortions.

image-anonymization privacy-preserving-AI computer-vision-research image-recognition-robustness data-privacy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Feb 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZamDimon/distortion-generator"

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