Introduction

Being able to extract text from an image and convert it to a String type can be a powerful app feature. Apps can read signs and use voice-over to help the visually impaired, and they can process paper forms by recognizing text at specific locations.

This lesson will focus on the special cases for text recognition. You’ll still use the request-to-handler-to-observation pattern, so working with text shouldn’t be that much of a stretch. You’ll also learn some tips and tricks for evaluating how well the recognition performed and adding filters to images where the text might be hard for the Vision framework to read.

By the end of the lesson, you’ll learn how to:

• Describe how to use the Vision framework for text detection and recognition tasks.
• Explain the accuracy and limitations of text detection and recognition.