Image Augmentor

Image Augmentor is a Python application that allows you to perform various image augmentation techniques on a folder of images. It provides an easy-to-use interface to choose from seven augmentation techniques and generate augmented images for each technique.

Features

• Rotate (7): Generate seven rotated images from the input image.
• Shift (4): Generate four shifted images from the input image.
• Shear (3): Generate three sheared images from the input image.
• Zoom (4): Generate four zoomed images from the input image.
• Flip (4): Generate four flipped images from the input image.
• Change Brightness (5): Generate five images with varying brightness levels from the input image.
• Add Noise (5): Generate five images with added noise from the input image.
• Simulate Cloud Effect (5): Generate five images with an added cloud effect from the input image.
• Simulate Fog Effect (5): Generate five images with an added Fog effect from the input image.
• Simulate Rain Effect (5): Generate five images with an added Rain effect from the input image.
• Simulate Snow Effect (5): Generate five images with an added cloud effect from the input image.
• Simulate Sun flare Effect (5): Generate five images with an added Sun flare effect from the input image.
• Generate a labeling file and annotation file

Usage

1. Clone the repository or download the source code.
2. Install the required dependencies (list the dependencies and versions if applicable).
3. Run the image_augmentor.py script.
4. Select the input image directory containing the images to augment.
5. Choose the save directory where the augmented images will be saved.
6. Select the desired augmentation library (Keras, imgaug, albumentations, or torchvision) from the menu.
7. Check the augmentation techniques you want to apply.
8. Click the "Apply Augmentation" button to start the augmentation process.
9. Optionally, generate a labeling file and annotation file for the augmented images using the provided buttons.

License

This project is licensed under the Apache 2.0 license. Please refer to the [LICENSE.md] file for more information.

Disclaimer

This application is provided for educational and non-commercial use only. The original creator, Taha Khamis, maintains the copyright of the code and you should obtain permission to use or distribute it.

Contributing

Contributions to this project are welcome. If you encounter any issues or have suggestions for improvement, please open an issue or submit a pull request.