Pytesseract

Back to Vision Docs

Pytesseract is a wrapper for Google’s Tesseract Optical Character Recognition Engine. Pytesseract allows for the detection of characters in an image. It has support for numerous languages and character sets.

Pytesseract is a wrapper, meaning it doesn’t contain much functionality on its own. Essentially, it provides a way to call tesseract’s command line tool from Python. Since there is a lack of sufficient documentation on Pytesseract, it is recommended that you look at tesseract’s documentation directly and then search for the equivalent Pytesseract function.

It’s most likely that you’ll be using either the image_to_string() function or the image_to_data() function. Both of these allow you to extract text and other data from an image.

To learn more, check out tesseract’s documentation.