In this python tutorial, we will go over how to extract text (using optical character recognition - OCR) from an image using pytesseract (with tesseract) and easyocr, how to extract text in different languages, and how to create a text file with the extracted text.
Note: If you have trouble installing easyocr, try creating a new package environment with a different python version such as 3.8. When I tried to install using python 3.10 I received an error - I am not exactly sure why and I am guessing this will be fixed eventually. I created a new Anaconda package environment using python 3.8, pip installed easyocr using terminal in that environment and everything worked.
Another Note: I created a new Anaconda package environment for ocr using Anaconda Navigator however the Jupyter Notebook icon was not visible to install so I pip installed it in the new environment using terminal (command line) instead.
install:
pip install notebook
run:
jupyter notebook