https://github.com/farzadshayanfar/textchaser

A generic OCR application.
https://github.com/farzadshayanfar/textchaser

ocr pyside6 python tesseract tesseract-ocr text-detection

Last synced: 17 days ago
JSON representation

A generic OCR application.

• Host: GitHub
• URL: https://github.com/farzadshayanfar/textchaser
• Owner: farzadshayanfar
• License: apache-2.0
• Created: 2023-05-13T11:33:35.000Z (about 3 years ago)
• Default Branch: master
• Last Pushed: 2023-05-20T05:48:35.000Z (about 3 years ago)
• Last Synced: 2025-01-02T01:45:07.939Z (over 1 year ago)
• Topics: ocr, pyside6, python, tesseract, tesseract-ocr, text-detection
• Language: Python
• Homepage:
• Size: 84.4 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          


# TextChaser

TextChaser is a gui application for

*[Google Tesseract OCR Engine](https://github.com/tesseract-ocr/tesseract)*. In addition to that, it also uses a

pretrained *[EAST model](https://arxiv.org/abs/1704.03155v2)* for text detection from scene images and then inputs the

detected boxes to Tesseract for

image to text conversion. The gui part is developed with *[PySide6](https://doc.qt.io/qtforpython-6/)*.

⚠️ This work is from a 2019 job I took for an English-Farsi OCR

application and currently is being heavily refactored and changed

so that it can be used for other languages and include more OCR engines

and scene text detection models. It might not work out of

the box right now. When I remove this message it will be functional.

![textchaser_demo_image_1](./github_readme_files/textchaser_demo_image_1.png)

# License

TextChaser is licensed under Apache 2.0 License.

# Credits

+ Developed by Farzad Shayanfar