Microsoft today announced Windows Vision Skills, a simple set of APIs that will allow Windows developers to easily build apps to solve complex computer vision problems. In this preview release, Microsoft has included WinRT APIs for object detection, skeletal detection and face sentiment. These APIs can be used in .NET, Win32, and UWP Windows applications. Developers can make use of hardware acceleration frameworks on Windows devices by packaging their solution as a Vision Skill.
- All Windows Vision Skills inherit the base classes and interfaces in Microsoft.AI.Skills.SkillInterfacePreview. This open framework can easily be extended to work with existing machine learning frameworks and libraries such as OpenCV.
- Windows Vision Skills complements existing Windows support for inference of ONNX models by utilizing WinML for local inferencing. The framework allows you to build intelligent applications while leveraging platform optimization.
You can check out the Nuget packages of Windows Vision Skills here.