Skip to content

Latest commit

 

History

History
264 lines (197 loc) · 9.53 KB

README.md

File metadata and controls

264 lines (197 loc) · 9.53 KB
Raw

Contributors License: GPL v3 tensorflow badge keras badge OpenCV scipy

logo


Convert Image Maker

Graduation project using image conversion & GAN
Explore the docs »

Table of Contents

About The Project

When you enter an image, it creates a transformed image with some modifications to the objects inside the original image.

캡처

Brief description

  • When you input an image, objects inside the image are detected through a suitable algorithm.
  • Various conversion methods (rotation, inversion, substitution with other objects, GAN conversion, etc.) are added to objects detected from the original image.
  • Create a new image by combining the original image and the converted object.

Motivation

The project started with creating the images needed for the spot the difference game. The spot the difference game is a game that finds different parts by comparing two similar images at a given time. In general, the game is played using a fixed image set in the local environment. With this problem in mind, I started a project that analyzes the input image and creates a similar transform image.

This project provides the ability to detect small objects inside the input image and convert the detected objects by applying various image processing techniques.

This project was developed in two parts, "Image Conversion Function" and "Android Application".
For information on Android apps using this repo, please refer to the following link.

Built With

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Prerequisites

This is an example of how to list things you need to use the software and how to install them.

  • OpenCV with contrib modules
pip install opencv-contrib-python
  • Scipy 1.2.0(Important)
pip install scipy==1.2.0
  • Pillow
pip install pillow
  • Tensorflow
pip install tensorflow==2.2.0
  • Keras
pip install Keras==2.2.0
  • Numpy
pip install numpy

Or you can install the libraries you need to use at once. It is suitable when using a new virtual environment (interpreter).

pip install -r requirements.txt

Installation

  1. Complete the prerequisite settings

  2. Clone the repo

git clone https://github.com/doljae/convert_image_maker.git

  1. Unzip the repo and put the folder in the path to use the library.

  2. Please refer to the manual to import and use the library.

  3. For detailed usage instructions, see user_guide.pdf

Usage

Please refer to the Wiki page

About GAN Model...

The GAN model is required for image conversion using the GAN model. Please put the GAN model in the directory below.

./pix2pix/your_gan_model.h5

We attach a link to download the GAN model for users who are in a condition where the model is difficult to learn, or who need quick testing.

(Note) The artificial intelligence model depends on the data used for learning. If you build a model with a lot of high quality data, you will get much better results.

For information on GAN, please refer to the link below.

Roadmap

See the open issues for a list of proposed features (and known issues).

Release History

  • 2.1.5
    • CHAGNE: Updated guide for image conversion with GAN model (2/3)
    • CHAGNE: Directory & structure description
  • 2.1.0
    • CHAGNE: Updated guide for image conversion with GAN model (1/3)
    • CHAGNE: Upload the created GAN model file (.h5) to an external drive.
  • 2.0.0
    • CHAGNE: Code refactoring(2/2)
    • CHANGE: Update docs (module code remains unchanged)
  • 1.5.0
    • CHAGNE: Code refactoring(1/2)
  • 1.0.0
    • The first release
    • FIX: Crash when calling GAN model file(.h5) with absolute directory
  • 0.5.0
    • The first function test
  • 0.2.0
    • Work in progress

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

  1. Fork the Project(https://github.com/doljae/convert_image_maker/fork)
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License

Distributed under the GPLv3 License. See LICENSE for more information.

Contact

Project Link: https://github.com/doljae/convert_image_maker/

Acknowledgements