VedaCare is an AI-powered health analysis and evaluation platform that leverages computer vision and machine learning to analyze facial and nail characteristics. The system assists Ayurveda experts in providing personalized, data-driven health insights through a simple and intuitive web interface.
The platform bridges traditional Ayurvedic knowledge with modern AI technologies, making health evaluation more accessible, scalable, and data-backed.
VedaCare analyzes facial and nail images/videos to identify potential health indicators and generate insights that can support Ayurvedic diagnosis.
The platform provides:
- 🧑⚕️ Analytical tools for Ayurveda practitioners
- 📊 Data-driven visual insights
- 🧑💻 A user-friendly interface for patients
- ☁️ Cloud-powered machine learning analysis
Capture high-quality facial and nail data through an intuitive interface.
Guided capture system ensures reliable data:
- Proper lighting instructions
- Correct camera positioning
- Optimal focus and framing
- Input validation for consistent image quality
This ensures the AI models receive clean and usable data for accurate analysis.
The system performs multi-stage analysis using computer vision and machine learning.
- Skin tone and texture
- Nail color variations
- Nail patterns and abnormalities
- Surface features and visual markers
Local Processing
- Lightweight analysis
- Instant feedback to users
- Reduced cloud dependency
Cloud Processing
- Advanced ML models
- Deeper health indicator analysis
- Secure cloud-based computation
Patients receive:
- Simple health summaries
- Easy-to-understand results
- Personalized wellness recommendations
The goal is to translate complex AI analysis into actionable guidance.
Experts gain access to:
- Detailed analytical reports
- Annotated images with visual indicators
- Graphs and visual diagnostic insights
This enables more informed and precise Ayurvedic evaluation.
Users upload face and nail images/videos through the web interface.
Quality validation ensures:
- Proper lighting
- Correct angles
- Clear focus
Initial feature extraction is performed locally:
- Quick analysis
- Instant feedback
- Reduced cloud computation load
Advanced models perform deeper analysis in the cloud.
- ML-driven feature evaluation
- Health indicator detection
- Secure storage of results
Results are presented through two interfaces:
Patients
- Simple health summaries
- Wellness suggestions
Experts
- Detailed annotated reports
- Visual markers on images
- Data visualizations for diagnosis
- Django (Python) — Core backend framework and API development
- Flask — Lightweight ML inference services
- AWS — Cloud computing, storage, and scalable infrastructure
- React.js — Component-based UI architecture
- Vite.js — Fast development and build tooling
- Tailwind CSS — Modern and responsive UI design
- React Query — Efficient data fetching and caching
- Canvas API
- Image overlays for AI results
- Visual annotations for expert diagnostics
- Access simplified health insights
- Receive personalized wellness guidance
- Support clinical evaluation with AI insights
- Improve diagnostic accuracy using visual analytics
🥇 Top 10 Finalist — DevQuest Hackathon, IIT Jodhpur
Selected among 200+ competing teams for building an innovative AI-based healthcare analysis platform.
The project was recognized for:
- Applying AI and computer vision in healthcare
- Bridging traditional Ayurveda with modern technology
- Creating a scalable and practical diagnostic support tool
Planned improvements for VedaCare include:
- 🤖 Advanced ML models for additional health indicators
- 📱 Mobile application support
- 📈 Long-term health tracking and analytics
- 🔁 Expert feedback loop for continuous model improvement
Naitik Gupta and Team
⭐ If you found this project interesting, consider starring the repository!