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 · Mini Project
Hand Gesture Recognition
Webcam hand landmarks classified into gestures that control media
1-2 weeks build
Overview
MediaPipe tracks 21 hand landmarks per frame from an ordinary webcam; the kit normalises them for position and scale and feeds them to a small classifier trained on gestures you record yourself. Recognised gestures play, pause, skip and change volume on the system media player, with a debounce so one wave is one command.
What makes it stand up
- 01Real-time 21-point hand landmark tracking on a laptop CPU
- 02Wrist-relative, scale-normalised features that ignore hand position
- 03Recording tool to capture and label your own gesture set
- 04Debounced gesture-to-command mapping for media keys and volume
- 05Confusion matrix and per-gesture F1 reported in the notebook
Module breakdown
- 01
Capture
Webcam loop with MediaPipe Hands and an on-screen landmark overlay.
- 02
Dataset tool
Keypress labelling that writes landmark rows to CSV.
- 03
Classifier
Random forest and MLP compared on the same normalised features.
- 04
Controller
Maps stable predictions to media and volume actions.
- 05
Evaluation
Train-test split, confusion matrix and latency per frame.
After this, you will be able to
- Explain why landmarks beat raw pixels for gesture classification
- Defend your normalisation and debounce choices
- Demo live media control in front of examiners
Technology stack
- Python
- MediaPipe
- OpenCV
- scikit-learn
- Pandas
- Level
- Mini Project
- Domain
- Artificial Intelligence
- Build time
- 1-2 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