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
Eye Disease Classification with ResNet & VGG19
Compares ResNet and VGG19 on cataract, glaucoma, DR and normal eyes
2-3 weeks build
Overview
Trains ResNet50 and VGG19 side by side on a public four-class fundus dataset covering cataract, glaucoma, diabetic retinopathy and normal eyes. Both models share the same splits and augmentation, so the report can compare them fairly on per-class F1, training time and model size.
What makes it stand up
- 01Head-to-head ResNet50 versus VGG19 under identical conditions
- 02Four-class fundus dataset from public Kaggle and ODIR sources
- 03Frozen-then-unfrozen fine-tuning schedule for both backbones
- 04Per-class metrics, confusion matrices and Grad-CAM for each model
- 05Academic screening prototype, not a clinical diagnostic
Module breakdown
- 01
Dataset
Class balancing, stratified splits and consistent resizing.
- 02
ResNet50 branch
Transfer learning with residual backbone and custom head.
- 03
VGG19 branch
Same pipeline on VGG19 for a like-for-like comparison.
- 04
Comparison
Metrics, parameter counts and inference time side by side.
- 05
Web demo
Flask page that runs both models on one uploaded image.
After this, you will be able to
- Explain how residual connections change what a deep network can learn
- Defend your fair-comparison setup between the two architectures
- Demo both models disagreeing and agreeing on real images
Technology stack
- Python
- TensorFlow
- Keras
- OpenCV
- Flask
- 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