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
Satellite Land-Use Classification
Classifies Sentinel-2 tiles into ten land-use classes with EuroSAT
2-3 weeks build
Overview
Trains land-use classifiers on the EuroSAT dataset, which labels Sentinel-2 tiles as forest, river, residential, crops and six other classes. RGB and full 13-band inputs are compared to show what extra spectral bands add, and a map view stitches predictions over a larger scene to estimate the share of each land-use type.
What makes it stand up
- 01Ten-class land-use model trained on EuroSAT
- 02RGB versus all 13 spectral bands compared directly
- 03NDVI and other band indices as engineered features
- 04Scene-level map with land-use percentages
- 05Confusion matrix and per-class F1 in the report
Module breakdown
- 01
Data
EuroSAT RGB and multispectral loaders with stratified splits.
- 02
Models
Fine-tuned ResNet for RGB and an adapted first layer for 13 bands.
- 03
Band indices
NDVI and water index computed as extra inputs.
- 04
Scene mapping
Sliding-window predictions over a larger tile.
- 05
Analysis
Land-use breakdown charts and per-class errors.
After this, you will be able to
- Explain what near-infrared bands reveal about vegetation
- Compare RGB and multispectral models with evidence
- Demo a land-use map over a region the examiner picks
Technology stack
- Python
- PyTorch
- Rasterio
- Pandas
- Streamlit
- 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