LeviBorodenko/img2rag
Convert any image into a Region Adjacency Graph (RAG)
This tool helps researchers and analysts in computer vision by converting images into a structured graph representation. You provide an image, and it outputs a graph where each node represents a distinct region of the image, complete with attributes like color, size, and location. This is useful for those who need to analyze image content in terms of relationships between different visual elements, such as scientists studying biological samples or security analysts examining satellite imagery.
No commits in the last 6 months. Available on PyPI.
Use this if you need to analyze an image's composition by breaking it down into perceptually distinct regions and understanding how those regions relate to each other.
Not ideal if you're looking for a general-purpose image segmentation tool or if your primary goal is simple object detection within an image.
Stars
12
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 27, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/LeviBorodenko/img2rag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents