Project Overview
A web application that enables users to upload images and apply painting-style transfers to them. Developed using the Flask Framework and incorporates generator models trained with TensorFlow, following the CycleGAN architecture.
Key Features
- Generate painting-style images from uploaded pictures
- Classify uploaded images into different categories with corresponding probabilities
- View color histogram analysis of uploaded images
- Real-time image processing with TensorFlow models
- Responsive web interface with Bootstrap styling
Technical Implementation
The application uses a CycleGAN (Cycle-Consistent Adversarial Networks) architecture to perform unpaired image-to-image translation. This allows the model to learn mappings between different image domains without requiring paired training data.