Group Group Group Group Group Group Group Group Group

Tesseract OCR Tutorial for iOS |

In this tutorial, you’ll learn how to read and manipulate text extracted from images using OCR by Tesseract.

This is a companion discussion topic for the original entry at

Hi Thanks for this tutorial. when I add “let preprocessedImage = scaledImage.preprocessedImage() ?? scaledImage” I get the following warning "Value of type ‘UIImage’ has no member ‘preprocessedImage’ "

Hi, sorted it out function preprocessedimage was not in right place!

@maufox Glad you fixed it! Cheers! :]

can we scan car number plate please make tutorial on number plate scanning using tesseract.

@khanfaheem Thank you for your suggestion - much appreciated! I will forward it to the tutorial team.

This tutorial shows you how to extract textual information from an image. That covers what you’d need to do for number plates as well. We won’t be making an additional tutorial to cover that topic.

Great tutorial, But I have a question, how can I get more trained language data? like Russian、Chinese language etc.

@lyndsey Can you please help with this when you get a chance? Thank you - much appreciated! :]

@block The link to more language data is in the final section of the tutorial. (Tap "download more language data.”)

Hey, beginner here! Love the tutorial! I was wondering, however, if there is a way for me to specifically find bold or italics words in a photo rather than return all the words. That is, how can I extract a subset from the full list of words detected by the OCR?