softwareCompleted
Signed Language
Hands + Face + Pose
Tracking
KNN (k=3)
Model
Incremental
Learning
// Overview
Real-time gesture recognition using MediaPipe hand/body tracking combined with a custom-trained KNN classifier. Features incremental learning, 3× data augmentation, and temporal dynamics analysis.
// Problem
~250,000 people in Kurdistan with hearing/speech difficulties need accessible communication tools without expensive hardware.
// Solution
Built a software-only gesture recognizer using MediaPipe (hands, face mesh, pose) and a KNN model with incremental training, confusion tracking, and augmentation — works with any standard webcam.
// Impact
Demonstrates that sign language recognition is achievable with zero specialized hardware, using only a laptop camera.
// Tech Stack
AIPythonMediaPipeKNNscikit-learn