Demo using MediaPipe to control a webpage using facial gestures

It is a react application that uses streaming webcam to estimate 468 3D face landmarks in real-time.

Official academic page for the paper: "Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images" (WACV 2025)

SQUAT DETECTION USING MEDIAPIPE IN JAVASCRIPT

Official page of the paper: "IS IN-DOMAIN DATA BENEFICIAL IN TRANSFER LEARNING FOR LANDMARKS DETECTION IN X-RAY IMAGES?"

Official academic page for the paper: "Are X-ray landmark Detection Models fair? A preliminary assessment and mitigation strategy" (ICCV 2025 Stream Workshop)

This web application utilizes React and the MediaPipe Holistic model to facilitate real-time detection of facial and hand landmarks via webcam. It analyzes head orientation, tracks eye blinking, and visually represents landmarks and connections on an interactive canvas. Furthermore, it optimizes performance by efficiently logging relevant data .

Focus Detection System

An advanced AI-powered webpage for real-time detection of face gestures, landmarks, age, and gender. Built for precision and designed for intuitive use, Gestura brings facial recognition technology to your fingertips.