Super-Resolution GAN Flask Web Application

Introduction

This project demonstrates a practical application of Generative Adversarial Networks (GANs) for image super-resolution, enhancing low-resolution images to high-resolution. The project utilizes Flask to create a web application, allowing users to upload images and receive enhanced versions. The GAN model employs advanced techniques, including hyper-parameter tuning, to achieve remarkable results in image quality enhancement.

Features

• Image Enhancement: Transform low-resolution images into high-resolution using GANs.
• Web Application: A Flask-based interface for easy image uploading and processing.
• Advanced Techniques: Incorporation of hyper-parameter tuning and deep learning methodologies for optimal image enhancement.

Technology Stack

• Python
• Flask
• GAN (Generative Adversarial Network)
• HTML/CSS (for the web interface)

Setup Instructions

Prerequisites

• Ensure you have Python 3.6+ installed on your system.

Installation & Running

1. Clone the repository:

   git clone https://github.com/asharmas23/Flask_webapp_SRGAN.git
   

2. Navigate to the project directory:

   cd Flask_webapp_SRGAN

3. To run the Flask application, open the flask.ipynb notebook in a Jupyter environment and execute the cells.

Usage

Select Image: Via the web interface, users can select a low-resolution image they wish to enhance.

View Results: The application processes the image and displays the enhanced super-resolution image alongside the original for comparison.

Demo Video

Watch the project demo.

Contributing

Contributions to the project are welcome. This can include adding new features, improving the model's efficiency, or enhancing the web interface. Please follow the standard GitHub fork and pull request workflow.

Conclusion

This project showcases the power of GANs for super-resolution imaging, providing a user-friendly platform for practical application. Future work will focus on improving the model's architecture and efficiency.