Pytesseract Image to Text Extraction Project

Description

• This project utilizes the Pytesseract library, a Python wrapper for Google Tesseract-OCR, to extract text from images. The goal is to provide a simple interface for users to convert images containing text into machine-readable text.

Objectives

• To demonstrate the capabilities of Optical Character Recognition (OCR) using Pytesseract.
• To provide a user-friendly tool for text extraction from various image formats.

Target Audience

• Developers, researchers, and anyone interested in text extraction from images.

Features

• Extracts text from images in various formats (JPEG, PNG, etc.)
• Supports multiple languages (if Tesseract is configured accordingly)
• Simple command-line interface for ease of use
Option to save extracted text to a file

Configurations

1. To download tesseract on windows →https://github.com/UB-Mannheim/tesseract/wiki
2. Install pytesseract Python Wrapper:
   Once Tesseract is installed, you can install the pytesseract Python wrapper, which allows you to interact with Tesseract via Python:
   — pip install pytesseract
3. Configuring pytesseract in Your Python Script

Make sure to configure pytesseract to know the location of the Tesseract executable if you haven't added Tesseract to your system path.

Set-up

1. Make sure you installed all the dependencied by running the install command in the main folder => pip install -r requirements.txt
2. Navigate to the flask app folder, where the app.py is and run the following command in terminal => python app.py
3. Open the browser and type in the localhost:5000 in the address bar
4. That's it! Enjoy

Conclusion

This project demonstrates how to use Pytesseract for text extraction from images. It can be further enhanced by adding features such as language selection, image preprocessing, and a graphical user interface (GUI).

References

Pytesseract Documentation https://pypi.org/project/pytesseract/
Tesseract-OCR GitHub Repository