Leave a Comment / ML & AI, Tech-Stack / By
OpenCV And Tesseract
OpenCV And Tesseract

The release of OpenCV and Tesseract at Vivify Healthcare is part of the company’s research and development efforts to find the best technology stack that is both sustainable and affordable.

OpenCV (Open Source Computer Vision) and tesseract are two separate Python libraries commonly used for image processing and optical character recognition (OCR), respectively. OpenCV provides tools for image manipulation, including reading, writing, and processing images, while tesseract is a wrapper for the Tesseract OCR engine, which allows text to be extracted from images.

Purpose of using OCR

To convert data from Non-readable text to Readable text using Python, we are using the OpenCV, tesseract, library to to convert Image to a simple text file using OCR . Moreover Pillow, Scikit-Image, Pgmagick can be also used as an library for the OCR Conversion.

OpenCV And Tesseract_1

Optical character recognition

OCR stands for Optical Character Recognition. It is a technology that recognizes text within a digital image. commonly used to recognize text in scanned documents and images. OCR software can be used to convert a physical paper document, or an image into an accessible electronic version with text.

Tesseract

Tesseract is an optical character recognition engine for various operating systems. It is free software, released under the Apache License. Originally developed by Hewlett-Packard as proprietary software in the 1980s, and released as open source in 2005 and development have sponsored by Google. For more details Tesseract.

Opencv

Opencv Open Source Computer Vision Library is an open source computer vision and machine learning software library. Built to provide a common infrastructure for computer vision applications to accelerate the use of machine perception in the commercial products. Apache 2 licensed product, OpenCV makes easy for businesses to utilize and modify the code. For more details opencv.

Installation

Follow the bellow steps for required packages

  • Clone the repositry
  • Create Virtul Environment and activate it
    python -m venv venv
  • make sure in correct directory. our case inside cloned repository folder
  • run this command to install required packages pip install -r .\requirements.txt, once installation success,
  • sudo apt install tesseract-ocr -y
  • sudo apt install tesseract-ocr-heb
  • sudo apt install tesseract-ocr-all -y for all languages, default language is English
  • run the file ocr_tesseract.py

Additional Setup for Windows

  • download the file exe from tesseract web or github .
  • Install the tesseract.exe and while installation copy the path
  • After done the installation, Open Environment varibales in Your PC.
  • Add Path ( copied while installing)
  • Add variable TESSDATA_PREFIX=Your tesseract path\tessdata
  • In your code add this line and path of tesseract

pytesseract.pytesseract.tesseract_cmd = r"\tesseract.exe"

Note : That path must contain bin,tessdata folders

How it works

  • First we are opening an Image, which we have to convert
  • Then, finding boxes using opencv and draw the box with green indication around box, then we capture the bounding values x,y,height and width and save them into the variables.
  • Now, cropping the image with bounding values. X,Y values for start point and height, width values for draw the box.
  • Send to pyTesseract, That’s it the output value or recognized text stored at text variable.
Skip to content