Art of Mithila - AI-Powered Cultural Heritage Classifier
An innovative web application that leverages deep learning and computer vision to classify traditional Nepali art forms including Mithila Painting, Thangka Painting, Mandala Art, and Paubha Painting. Built with Next.js 15 frontend, Django backend, and a custom-trained VGG16 transfer learning model that achieves high accuracy in art classification with confidence scoring and alternative predictions.
Project Gallery
About This Project
This project represents a unique fusion of cultural heritage preservation and cutting-edge artificial intelligence technology. I developed a sophisticated deep learning system that can accurately identify and classify traditional Nepali art forms using advanced computer vision techniques. The application features a modern Next.js 15 frontend with responsive design, a robust Django Python backend with RESTful API architecture, and a custom-trained VGG16 transfer learning model that processes uploaded images to predict art types with high accuracy. The system includes advanced image preprocessing, real-time classification with confidence percentages, Cloudinary integration for optimized image handling, and provides users with detailed predictions including top matches and alternative classifications. This project demonstrates the potential of AI in preserving and understanding cultural heritage while showcasing expertise in full-stack development, machine learning, and computer vision technologies.
Key Features
- Deep learning image classification for traditional art
- VGG16 transfer learning model implementation
- Real-time image upload and processing
- Confidence percentage display for predictions
- Alternative classification suggestions
- Cloudinary integration for image optimization
- Responsive web interface design
- RESTful API architecture
Challenges & Solutions
- Training accurate models with limited art dataset
- Implementing transfer learning with VGG16 architecture
- Optimizing image preprocessing for different art styles
- Creating intuitive user interface for complex AI predictions
- Integrating frontend and backend seamlessly