PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Capstone
3D Face Reconstruction from Landmarks
Builds a textured 3D face mesh from a single photograph
4-5 weeks build
Overview
MediaPipe Face Mesh estimates 468 3D landmarks from one photo, and the kit turns them into a proper mesh: triangulation, head-pose estimation with solvePnP, texture mapping from the source image and export to OBJ. A Three.js viewer lets you rotate the reconstructed face, and the report measures landmark stability across poses and lighting.
What makes it stand up
- 01Dense 3D landmarks from a single image or webcam frame
- 02Head-pose estimation with OpenCV solvePnP
- 03UV texture mapping from the original photo
- 04OBJ export and an interactive Three.js viewer
- 05Landmark stability measured across pose and lighting changes
Module breakdown
- 01
Landmarks
MediaPipe Face Mesh with refined eye and lip points.
- 02
Mesh building
Triangulation and normal computation over landmarks.
- 03
Pose
Rotation and translation estimated with solvePnP.
- 04
Texture
Per-vertex UV mapping from the source image.
- 05
Viewer
Three.js page to orbit, light and export the mesh.
After this, you will be able to
- Explain how 2D images yield depth estimates for landmarks
- Defend the limits of single-view reconstruction
- Demo a rotating 3D model of your own face
Technology stack
- Python
- MediaPipe
- OpenCV
- NumPy
- Three.js
- Level
- Capstone
- Domain
- Artificial Intelligence
- Build time
- 4-5 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support