ShubhamManachekar's picture
Upload 13 files
826e4da
|
Raw History Blame Contribute Delete
2.15 kB

OCR Utility

Welcome to the OCR Utility, where text extraction from images and documents becomes a breeze! This tool utilizes powerful libraries to help you unveil hidden words and secrets.

Overview

The OCR Utility allows you to extract text from various file formats, including images (PNG, JPEG, TIFF) and documents (DOCX, PDF). It employs both Tesseract OCR and EasyOCR for accurate and multilingual text recognition.

Features

  • Extract text from images (PNG, JPEG, TIFF).
  • Extract text from DOCX files.
  • Extract text from PDF files with the help of Poppler.
  • Utilize Tesseract OCR and EasyOCR for precise text recognition.
  • Enhance images before processing for better results.

Requirements

Before you start your magical journey, make sure you have the required ingredients:

  • Python 3.6+: The enchanting language that powers the utility.
  • numpy: The essence of number-crunching magic.
  • Pillow (PIL): Your trusty wand for image manipulation.
  • pytesseract: The all-seeing eye for text extraction.
  • easyocr: The ancient tome of multilingual text deciphering.
  • python-docx: The scroll for unveiling secrets from DOCX files.
  • pdf2image: The spellbook for converting PDFs into images.
  • Tesseract OCR: Download and set the path to the executable.
  • Poppler for Windows: Download and remember the path for PDF handling.

For detailed instructions on obtaining these ingredients, check out the Requirements Guide.

Usage

  1. Clone the repository to your local machine.
  2. Install the required Python packages using pip install -r requirements.txt.
  3. Follow the steps in the Requirements Guide to set up Tesseract OCR and Poppler for Windows.
  4. Run the main.py script and follow the prompts to extract text from your desired file.

Contribution

Contributions are welcome! If you find issues or have ideas for improvements, feel free to open an issue or submit a pull request.

Credits

This utility was created by [Your Name] as a project inspired by the magic of text extraction.

License

This project is licensed under the MIT License.