Colorizing Black and White Images using Deep Learning and Deploying with Django Backend

Project Overview

This project involves the colorization of black and white images using deep learning techniques. The colorization model was trained to predict appropriate colors for grayscale images, effectively adding color to historical and monochromatic photographs.

The project also includes a web application with a Django backend, allowing users to upload black and white images and receive their colorized versions.

Team Members

• Shivnath Chavan
• Ayush Mudgal
• Kshitij Murabatte
• Saksham Sharma
• Vaibhav Hariramani The Vaibhav Hariramani App (Latest Version)                    

Project Links

• GitHub Repository: Image-Colorisation-Algorithms
• Deployed Model: https://imagecolorisation.herokuapp.com/

Web Application Screenshots

Training the Model

To train the model:

1. Fork the main repository: Image Colorisation
2. Navigate to ApproachByRzang_ECCV16 within the repository.
3. Run the provided Jupyter notebook or the execute.py script to train the model with the desired parameters.

Deploying the Model on Heroku

To deploy the model on Heroku:

1. Sign up or log in to Heroku.
2. Create a new app and connect it to your model's GitHub repository.
3. Deploy the model using Heroku's deployment process.

Resources

To learn more about these Resources you can Refer to some of these articles written by Vaibhav Hariramani:-

• Medium
• geeky Traveller
• Blogs
• Youtube   

Conclusion

The project successfully combined deep learning techniques with web development to create a colorization model with a user-friendly web interface. The collaboration between team members showcased the power of interdisciplinary teamwork in achieving innovative results.

License

This project is licensed under the MIT License - see the LICENSE file for details.