Skip to content

kariemoorman/imagextract

Repository files navigation

imagextract

diagram

A MacOS command-line application for extracting text, objects, and faces from image files using Apple Vision and CoreML APIs.


Installation

Imagextract requires Mac OS version 13 or greater to access the latest VisionKit APIs.

  1. Open Terminal
  2. Run the following curl command:
curl -L https://github.com/kariemoorman/imagextract/raw/main/install.sh | bash
  1. Reload terminal configuration file to incorporate new PATHs:

For ZShell users,

source ~/.zshrc

For Bash users,

source ~/.bashrc

Usage

imagextract IMAGE_FILE.[png|jpg|jpeg|pdf|tiff]

Example

Example

Output: imagextract: Proof of Concept

License

MIT

Contributions

Contributions are welcome. Please submit an issue or feel free to fork and contribute a pull request.

Acknowledgements

Inspired by projects such as Textra by Dylan Freedman and ObjectDetection-CoreML by tucan9389.

About

A MacOS command-line application to extract information from image files (JPG, PNG, TIFF, PDF) using Apple Vision and CoreML APIs.

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors