Our application can now see what the user sees, but, currently, we have no way of understanding what the user is looking at. We will resolve this in this section, where we will implement our FrameAnalyzer class, which will pass our captured frames to Microsoft's Cognitive Vision API Service to extract the tags and caption.
Let's start by creating a new class. Within Visual Studio, create a new C# Class in the Content folder named FrameAnalyzer. At the top of the newly created class, add the following namespaces to get access to Microsofts Cognitive Services SDK:
using System.IO;using System.Threading;using Microsoft.ProjectOxford.Vision;using Microsoft.ProjectOxford.Vision.Contract;
As we did with FrameGrabber, we will build ...