twitter-research/image-crop-analysis

Code for reproducing our analysis in the paper titled: Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

45
/ 100
Emerging

This project helps social media platforms and content moderators analyze how automated image cropping algorithms might introduce bias, specifically focusing on fairness and representation. You input images that have been processed by an image cropping algorithm and get back an analysis of potential demographic biases in how faces are cropped. This is useful for anyone designing or implementing AI-driven content presentation systems, such as product managers, ethical AI researchers, or platform policy makers.

253 stars. No commits in the last 6 months.

Use this if you need to evaluate the fairness of an image cropping algorithm and understand its impact on demographic representation.

Not ideal if you are looking for a general image processing library or a tool to perform image cropping itself.

ethical-AI content-moderation social-media-design algorithmic-bias fairness-metrics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

253

Forks

41

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Oct 25, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/twitter-research/image-crop-analysis"

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