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
Sports Activity Recognition
Identifies the sport being played from a photo or a short video clip
2-3 weeks build
Overview
A transfer-learning classifier trained on a public Kaggle sports image dataset. For images it predicts the sport with top-3 probabilities; for video it samples frames, classifies each and aggregates the votes into one label with a per-segment timeline. Grad-CAM heatmaps show which part of the frame drove each decision.
What makes it stand up
- 01Fine-tuned ResNet and EfficientNet compared on the same split
- 02Frame sampling and vote aggregation for video input
- 03Per-segment timeline for clips that switch between sports
- 04Grad-CAM heatmaps for every prediction
- 05Web upload interface with top-3 probabilities
Module breakdown
- 01
Data pipeline
Loading, class balancing and augmentation of the image set.
- 02
Training
Transfer learning with frozen then unfrozen backbone stages.
- 03
Video inference
Uniform frame sampling and majority-vote aggregation.
- 04
Explainability
Grad-CAM overlays on the final convolutional layer.
- 05
Web app
Flask inference API and React upload view.
After this, you will be able to
- Explain transfer learning and why you froze what you froze
- Defend frame-voting against a true temporal model
- Demo predictions with heatmaps on unseen clips
Technology stack
- Python
- PyTorch
- OpenCV
- Flask
- React
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 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