Image Processor

The Image Processor is a Python application that allows you to process a batch of images by applying various image processing techniques. It provides a graphical user interface (GUI) for easy interaction and offers features such as image enhancement, foreground extraction, and background healing.

• Batch processing of images
• Human detection using the MobileNetV3 model
• Foreground extraction using the U-2 Net model
• Background healing and inpainting
• Progress tracking and logging

• Python 3.10

1. Clone the repository or download the source code.
2. Install the "Requirements.txt" using pip: pip install -r Requirements.text

1. Run the app/main.py script:

python app/main.py

2. The Image Processor GUI will open.
3. Select the input folder containing the images to be processed.
4. Select the output folder where the processed images will be saved.
5. Adjust any desired image processing parameters.
6. Click the "Start Processing" button to begin the image processing.
7. The progress bar will indicate the processing progress.
8. The output log will display the names of the processed images and any relevant messages.
9. Once the processing is complete, a message will be displayed indicating the finish.

Please refer to the User Manual for detailed instructions on how to use the Image Processor application.

The Image Processor makes use of the following libraries and models:

• Tkinter: https://docs.python.org/3/library/tkinter.html
• PIL (Python Imaging Library): https://pillow.readthedocs.io/en/stable/
• OpenCV: https://docs.opencv.org/
• MobileNetV3: https://arxiv.org/abs/1905.02244
• U-2 Net: https://arxiv.org/abs/2005.09007

The Image Processor project was inspired by the need for a simple and efficient tool to process a large number of images with various image processing techniques. The development of this application was made possible by the contributions of many individuals who generously shared their knowledge and expertise.