Saram - Image/PDF OCR detection system

Get OCR in txt form from an image or pdf extension supporting multiple files from directory using pytesseract with support for rotation in case of wrong orientation along.

Currently in beta state

Follow: Demo run

Note: Make sure you have a OCR tool like tesseract and certain data value for comparing OCR, eg tesseract-data-eng along with Pillow and Wand for image conversion and loading which will be fetched during pip install.

For using in python: Refer to the py-module branch

Installation

Install using PIP:

$ pip install saram
$ saram <dirname>

else

Clone the source locally:

$ git clone https://github.com/aryaminus/saram
$ cd saram
$ git checkout py-module
$ python main.py <dirname>

Todo

• Add support for PDF by PDF -> Image -> Txt with converted image deletion after processing
• Double check for orientation in case of image and PDF
• Make a PIP package
• Add NLP to process the most repeated frequent characters to filer content
• Add Cloud Vision support for effective character recognization
• Suppot for GUI using tkinter

Reference

1. pdf-to-txt
2. ocr-convert-image-to-text
3. fix-image-rotation
4. python-packaging

---

Contributing

1. Fork it (https://github.com/aryaminus/saram/fork)
2. Create your feature branch (git checkout -b feature/fooBar)
3. Commit your changes (git commit -am 'Add some fooBar')
4. Push to the branch (git push origin feature/fooBar)
5. Create a new Pull Request

Enjoy!