/Akshara-Jaana

A OCR Project for Reading New and Old Kannada Texts

Primary LanguagePython

AksharaJaana

An OCR for Kannada.

pypi

AksharaJaana is a package which uses tesseract ocr in the backend to convert the read-only kannada text to editable format. A Special feature of this is it can separate columns in the page and thus making it easier to read and edit. Do consider using this package if necessary and feel free to mail me for any clarifications.

Happy coding and installing.

To see the python package visit https://pypi.org/project/AksharaJaana/

The Requirements

Conda environment is preferred for the smooth use

  • AksharaJaana (pip package), check out the latest version available
  • Tesseract
  • poppler

Details for Installation

Ubuntu

Open terminal and execute below commands.

  1. Install the requirements in your system

    sudo apt-get update -y 
sudo apt-get install -y poppler-utils python3 python3-venv tesseract-ocr tesseract-ocr-kan

  2. Installing packages for AksharaJaana

    pip install --upgrade AksharaJaana

Windows

  1. Installing tesseract-ocr in the system

    • Download tesseract
      • go to the website
      • click on tesseract-ocr-w64-setup-v5.0.0-alpha.20200328.exe (64 bit).
    • Install tesseract for Kannada Language and Script
      • open the downloaded file and click next and accept the agreement.
      • Next you will give an option to choose the languages.
      • Choose kannada in both script and language
    • Add tesseract to Path
      • Check if this folder C:\Program Files\Tesseract-OCR\ is present. If yes, follow below procedure
      • Add C:\Program Files\Tesseract-OCR\ to your system PATH by doing the following
        1. Click on the Windows start button, search for Edit the system environment variables, click on Environment Variables
        2. Under System variables, look for and double-click on PATH, click on New.
        3. then add C:\Program Files\Tesseract-OCR\, click OK.
      • if folder is not present, manually add the folder tesseract-ocr to the Program Files in the C drive which must be present at the download section (after extraction) and follow the same procedure
      • See complete docs.

  2. Installing poppler in the system

    • Download Poppler
      • go to this page
      • click on poppler-0.54_x86
    • Unzip the file and copy files to C:\Users\Program Files\poppler-0.68.0_x86
    • Add poppler to path
      • Add C:\Program Files\poppler-0.68.0_x86\bin to your system PATH by doing the following:
        1. Click on the Windows start button, search for Edit the system environment variables, click on Environment Variables
        2. under System variables, look for and double-click on PATH, click on New
        3. then add C:\Users\Program Files\poppler-0.68.0_x86\bin, click OK.

  3. Installing python and pip in the system (If pip is not installed)

  4. Installing packages for AksharaJaana

    • open command prompt

      pip install AksharaJaana

  5. Reboot the system before starting to use

Python Script

Open In Colab

from AksharaJaana.main import OCREngine
from AksharaJaana.utils import ModelTypes, FileOperationUtils

ocr = OCREngine(modelType=ModelTypes.Easyocr)
# choices are Paddleocr, Easyocr, Tesseract

text = ocr.get_text_from_file("Your file Path") 
print(text)