bramtoula/vdna

Pytorch implementation of Visual DNA, an approach to represent and compare images.

42
/ 100
Emerging

This project helps you compare sets of images or even individual images by analyzing their 'visual DNA.' You input one or more image collections, and it generates unique numerical representations. This allows you to quantify how similar or different these images are, which is useful for anyone working with large image datasets who needs to understand visual relationships.

No commits in the last 6 months. Available on PyPI.

Use this if you need to objectively compare and group image datasets or find images similar to a reference set, based on subtle visual characteristics.

Not ideal if you're looking for a simple visual duplicate finder or only need to compare images using basic metrics like color histograms.

image-comparison visual-analytics dataset-similarity image-retrieval computer-vision-research
Stale 6m
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 10 / 25

How are scores calculated?

Stars

40

Forks

4

Language

Python

License

MIT

Last pushed

Feb 14, 2024

Commits (30d)

0

Dependencies

8

Get this data via API

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

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