Welcome to the Grayscale Image Colorization project repository! This project is dedicated to the fascinating task of colorizing grayscale images using advanced deep learning techniques. Our focus is on employing Convolutional Neural Networks (CNNs) to transform monochrome images into their vibrant, colorized counterparts.
Objective: To convert grayscale images into their colorized counterparts, enhancing their aesthetic and artistic value.
Target Audience: Ideal for artists, photographers, and technologists interested in the intersection of AI and image processing.
Python: Primary programming language, known for its efficiency and library support in AI and data science.
TensorFlow & Keras: For building and training the CNN model.
PIL (Python Imaging Library): For image manipulation and processing.
OpenCV: Utilized for advanced image processing tasks.
Scikit-image: For image color space transformations.
Matplotlib: For plotting and visualizing images.
Tkinter: For creating the graphical user interface (GUI).
Convolutional Neural Networks (CNNs): The backbone of our image colorization model. Data Augmentation: Enhancing the training process with techniques like shear, zoom, and rotation.
Jupyter Notebooks: For iterative coding and testing. Git & GitHub: For version control and repository hosting.
- Seamless conversion of black and white images to color.
- User-friendly GUI for easy interaction with the model.
- Robust model training with data augmentation.
- High accuracy and efficiency in image colorization.
Python 3.x and Pip (Python package manager)
Clone the repository:
git clone https://github.com/sushanthreddy009/Grayscale_Image_Colorization.git cd Grayscale_Image_Colorization
(Optional) Set up a virtual environment:
python -m venv venv source venv/bin/activate # For Unix systems .\venv\Scripts\activate # For Windows
Install dependencies:
pip install -r requirements.txt
Start the Application:
Run the main Python script to launch the GUI:
python main.py
Using the GUI:
- Once the GUI is open, you can select a grayscale image or a folder containing grayscale images for colorization.
- Use the 'Select file' or 'Select folder' buttons to choose your input.
- Click 'Start' to begin the colorization process.