Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Build the Finance Skills That Lead to Promotions, Not Just Certificates
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This tutorial builds a real-time body language decoder in Python by extracting facial and body landmarks from webcam video with MediaPipe and OpenCV. It covers collecting coordinate data, training and evaluating a custom Scikit-Learn pose-classification model, and adding new pose classes.
Syllabus
- Start
- Introduction
- How it Works
- Tutorial Start
- Installing Mediapipe and Dependencies
- Capture Landmarks using OpenCV and CSV
- Load Pose and Face Data using Pandas
- Train Sciki-Learn Pose Classification Model
- Evaluate Classification Model and Pickle
- Making Detections using the Model
- Decoded Body Language Demo
- Displaying Probabilities
- Adding in New Poses
- Wrap Up
Taught by
Nicholas Renotte