Using Tesseract, an open source library for performing Optical Character Recognition in Python.
This repository contains 2 python scripts for 2 different use cases:
- For performing OCR on images
- For performing OCR on PDFs
Run the respective python scripts for respective use-cases.
- Tesseract Core Library
- PyTesseract (Python wrapper for Tesseract Core)
- Pillow (For Image Processing)
- ImageMagick
- wand(Python binding for ImageMagick)
Tesseract was originally written in C++ and uses an LSTM Network behind the scenes, for more reading and installation guide, you can check out this very helpful blog post. This will explain you the essential stuff. I have also extended this for PDFs to make it more useful for real-world use-case.