Chapter 6Microsoft Cognitive Services

Now that you have learned how to obtain and display images from the camera and to synthesize and recognize human speech, you will use this knowledge to build a voice-controlled app powered by artificial intelligence (AI). Specifically, in this chapter, you will learn how to create a vision assistant app, called VisionAssistant. To achieve this, you will use the cloud-based Computer Vision API and Bing Web Search API from Microsoft Cognitive Services (MCS).

VisionAssistant will help visually impaired people by describing an image captured by the camera. (See Figure 6-1.) To accomplish this, it sends the image from the camera to the MCS system for processing. The system then analyzes the image and returns a ...

Get Programming for Mixed Reality with Windows 10, Unity, Vuforia and UrhoSharp, First Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.