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
Brain Tumour Detection Web App
Classifies brain MRI as glioma, meningioma, pituitary or no tumour
2-3 weeks build
Overview
A full web app around a CNN trained on a public four-class brain MRI dataset from Kaggle. Scans are skull-cropped and normalised, a pretrained model is fine-tuned, and the Next.js front end lets users upload a slice, see the predicted class and heatmap, and keep a history of past uploads.
What makes it stand up
- 01Public Kaggle brain tumour MRI dataset with four classes
- 02Automatic brain-region cropping before classification
- 03Fine-tuned pretrained CNN with per-class F1 in the report
- 04Grad-CAM heatmaps and upload history in the web app
- 05Academic screening prototype, not a neuro-radiology tool
Module breakdown
- 01
Preprocessing
Contour-based crop, resize and intensity normalisation.
- 02
Model
Pretrained backbone with a four-class head.
- 03
Inference API
FastAPI endpoint returning class, scores and heatmap.
- 04
Front end
Next.js upload flow, results page and history.
- 05
Evaluation
Confusion matrix and misclassification gallery.
After this, you will be able to
- Explain how the cropping step changes what the model learns
- Defend your evaluation against the dataset's known duplicates
- Demo the full upload-to-result flow in the browser
Technology stack
- Python
- PyTorch
- OpenCV
- FastAPI
- Next.js
- 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