The enduring popularity of devices with integrated cameras has caused apps that can interact with the real-world to grow in popularity. Learn to harness these latest technologies by creating an app that recognizes text viewed through your device’s camera, and converts it into spoken audio.
You will learn how to:
- Get started with Microsoft Azure cloud computing
- Create a computer vision API which receives images, and returns JSON files
- Understand JSON Files – How to use them, and how to extract relevant text
- Create a Speech API which receives JSON files and returns a speech audio file
- Send and receive server requests using Unity’s Web Requests
- Project the camera view onto the screen and display the text using Unity’s UI system and Webcam Textures
