RedVision
AI-powered anemia detection system using ML and computer vision to analyze fingernail color. Provides fast, non-invasive health assessment - users can monitor anemia risk anywhere with just a camera.
Winner of the Regional Award and Governor General's Award from Ingenious+ 2025.
.jpg)
Technologies Used
The Problem
Screening is slow and invasive for many people. I explored a quick image-based pre-screen to flag risk before a full test.
What I Built
A CV pipeline that crops the nail bed, normalizes color, and classifies anemic vs non-anemic. Served through a FastAPI endpoint with a tiny review UI for batch checks and spot audits.
Tech Notes
Python, OpenCV, PyTorch, lightweight CNN baseline, Docker, ROI extraction and color normalization. Small curated dataset with basic cross-validation. Research tool only, not a medical device.
Current Status
Experimental model with internal tests and error analysis.
What's Next
Better data capture guidelines, bias checks, calibration cards, and a simple mobile capture flow.