Introduction

The Vision Framework is the set of APIs Apple gives developers so apps can perform image analysis and other computer vision tasks on iOS and macOS devices. Using the Vision Framework, you can enable your apps to detect faces, read text, classify images, and other tasks using Apple’s provided AI models. You can even use CoreML to extend the framework with your own, trained AI models so your app can process images in ways specific to your app.

A great thing about the Vision Framework is that all the different kinds of requests follow a similar pattern. So once you’ve learned how to work with a few, you’ll be able to implement all the others with ease.

But the first task is to get images into your app. After some orientation, you’ll learn about that and then be ready to perform your Vision Framework magic!

By the end of this lesson, you’ll have learned to:

• Explain the core functionalities of the Vision framework for computer vision tasks on Apple devices.
• Discuss the advantages of using the Vision Framework for on-device computer vision.