francbianc/clothing_instance_segmentation

A supervised Deep Learning approach to clothing instance segmentation with Mask R-CNN

26
/ 100
Experimental

This project helps fashion retailers, e-commerce managers, or social media analysts automatically identify and outline individual clothing items in real-world photos, especially those from social media like Instagram. You provide unstructured images of people wearing clothes, and it outputs precise digital masks around each of 30 specific fashion items (like 'dress', 'jeans', 'hat'), separating them from the background and other items. This is useful for cataloging, trend analysis, or visual search.

No commits in the last 6 months.

Use this if you need to precisely locate and segment individual clothing items within "in the wild" images, such as user-generated content or lifestyle photos, rather than studio-quality pictures.

Not ideal if your primary need is general object detection or if you only work with highly controlled, clean images where backgrounds are uniform and items are clearly separated.

fashion-e-commerce visual-merchandising social-media-analytics apparel-inventory fashion-trend-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

23

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 17, 2022

Commits (30d)

0

Get this data via API

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

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