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 · Major Project
Bharatanatyam Mudra Recognition
Classifies classical dance hand mudras from images and live webcam
3-4 weeks build
Overview
Recognises Asamyukta hasta mudras, the single-hand gestures of Bharatanatyam, in two ways the report compares: a landmark classifier over MediaPipe hand keypoints and a fine-tuned CNN over cropped hand images. A live mode names the mudra being held and shows its meaning, which makes it usable as a practice aid.
What makes it stand up
- 01Two approaches compared: landmark classifier versus image CNN
- 02Hand cropping from MediaPipe boxes before CNN inference
- 03Capture tool to extend the dataset with your own recordings
- 04Live practice mode showing the mudra name and its meaning
- 05Per-mudra F1 and confusion analysis for look-alike gestures
Module breakdown
- 01
Dataset
Public mudra images plus a guided capture tool for new samples.
- 02
Landmark model
Normalised 21-point features into a dense classifier.
- 03
Image model
Transfer learning on MobileNetV2 with augmentation.
- 04
Live mode
Webcam inference with temporal smoothing of predictions.
- 05
Evaluation
Confusion matrix, per-class F1 and error gallery.
After this, you will be able to
- Explain why some mudras are confused and how you tackled it
- Defend the landmark-versus-CNN comparison in your report
- Demo live recognition of several mudras
Technology stack
- Python
- TensorFlow
- MediaPipe
- OpenCV
- Streamlit
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 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