boris-kz/CogAlg

This project is a Computer Vision implementation of general hierarchical pattern discovery principles introduced in README

59
/ 100
Established

This project offers a new way to help computer vision systems understand what they're seeing by finding patterns in images, starting from individual pixels. Instead of just learning from predefined examples, it discovers meaningful relationships and groups in visual data from the ground up. It's designed for researchers and engineers creating advanced image analysis and object recognition systems.

Use this if you are exploring new, unsupervised methods for hierarchical pattern discovery in visual data, aiming for more robust and explainable computer vision systems.

Not ideal if you need a pre-built, production-ready computer vision solution that relies on standard deep learning techniques and large labeled datasets.

computer-vision image-analysis pattern-recognition unsupervised-learning visual-intelligence
No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

98

Forks

40

Language

Python

License

MIT

Last pushed

Mar 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/boris-kz/CogAlg"

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