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
Breast Cancer Histopathology Classification
Separates benign from malignant tissue in histopathology patches
3-4 weeks build
Overview
Fine-tunes a CNN on the public BreakHis microscopy dataset to classify tissue as benign or malignant across several magnifications. Splits are made per patient to keep slides from one person out of both sets, stain normalisation evens out colour differences, and the app returns a label with a heatmap.
What makes it stand up
- 01BreakHis histopathology images at four magnification levels
- 02Patient-level splitting to avoid slide leakage
- 03Stain normalisation to reduce colour variation between labs
- 04Sensitivity, specificity and ROC curves in the report
- 05Academic research prototype, not a pathology diagnostic
Module breakdown
- 01
Data preparation
Patient grouping, magnification filters and splits.
- 02
Stain normalisation
Macenko-style colour normalisation on patches.
- 03
Model
Pretrained backbone fine-tuned for binary classification.
- 04
Explainability
Grad-CAM showing tissue regions behind each call.
- 05
Web app
Patch upload with label, confidence and heatmap.
After this, you will be able to
- Explain why patient-level splits matter in medical imaging
- Defend your choice of sensitivity as the headline metric
- Demo classification and heatmaps on unseen patches
Technology stack
- Python
- PyTorch
- OpenCV
- FastAPI
- React
- 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