gaze-detection and blink-detection
These are complementary tools—gaze detection tracks continuous eye position for interaction control, while blink detection identifies discrete eye state changes, and both could be integrated together to create more robust eye-based interfaces that respond to both where the user is looking and whether their eyes are open.
About gaze-detection
charliegerard/gaze-detection
đź‘€ Use machine learning in JavaScript to detect eye movements and build gaze-controlled experiences.
Leverages TensorFlow.js's face landmark detection model to classify gaze direction (RIGHT, LEFT, TOP, STRAIGHT) from webcam video streams in real-time. Provides a simple async API for loading the ML model, initializing camera input with device selection support, and continuously polling gaze predictions via `requestAnimationFrame`. Works cross-platform including mobile browsers, enabling developers to build interactive gaze-controlled interfaces without server-side processing.
About blink-detection
theankurkedia/blink-detection
Detect the user's blink and wink using machine learning
Scores updated daily from GitHub, PyPI, and npm data. How scores work