Optical Character Recognition - a set of activities, algorithms, or software to recognize characters and texts in an image file.
Simplifying this, it is getting a text from a graphic file by a computer program.
- pytesseract
- openCV
$ sudo apt-get update
$ sudo apt-get install libleptonica-dev
$ sudo apt-get install tesseract-ocr tesseract-ocr-dev
$ sudo apt-get install libtesseract-dev
$ sudo apt install python3-opencv
brew install opencv
brew install tesseract
download binary from https://github.com/UB-Mannheim/tesseract/wiki. then uncoment this line in script
pytesseract.pytesseract.tesseract_cmd = 'C:\Program Files (x86)\Tesseract-OCR\tesseract.exe'
Now you can install tesseract by pip
pip install tesseract
pip install tesseract-ocr
pip install pytesseract
and install openCV
pip install opencv-python