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
Skin Disease Detection with CNNs
Classifies dermatoscopic lesion images across seven HAM10000 classes
3-4 weeks build
Overview
Fine-tunes a pretrained CNN on the HAM10000 dermatoscopy dataset, part of the ISIC archive, to separate melanoma, nevi and five other lesion types. Splits are made by lesion ID so duplicate photos never straddle train and test, and a web app returns the top classes with a heatmap.
What makes it stand up
- 01HAM10000 images with seven lesion categories from the ISIC archive
- 02Lesion-ID aware splitting to prevent duplicate-image leakage
- 03Oversampling and focal loss for the heavily skewed classes
- 04Per-class recall with melanoma sensitivity called out in the report
- 05Academic screening prototype, not a substitute for a dermatologist
Module breakdown
- 01
Data pipeline
Metadata join, lesion grouping and stratified splits.
- 02
Augmentation
Colour, rotation and zoom transforms suited to skin images.
- 03
Model
Pretrained backbone fine-tuned with class-balanced loss.
- 04
Explainability
Grad-CAM overlays on the lesion region.
- 05
Web app
Upload flow with top-3 classes, confidence and disclaimer.
After this, you will be able to
- Explain why accuracy misleads on an imbalanced lesion dataset
- Defend lesion-level splitting as a leakage safeguard
- Demo predictions and heatmaps on held-out images
Technology stack
- Python
- TensorFlow
- Keras
- OpenCV
- Flask
- 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