Computer Vision Section 061
Faces, People and Pose
Finding people in pictures and describing them, plus the honest limits of doing that to human faces.
12 of 12 lessons published Three reading levels on every lesson
Lessons in order
Work top to bottom. Each lesson assumes the one above it.
- Face detection models
- Face alignment and landmarks
- Face embeddings and ArcFace
- Verification vs identification
- Face anti-spoofing and liveness
- Deepfake detection
- Bias and consent in face recognition
- Anonymising faces in a dataset
- Heatmaps for keypoints
- Top-down vs bottom-up pose estimation
- MediaPipe face, hand and body landmarks
- 3D human pose and SMPL