Announced Windows Vision Skills (Preview)

Recently, a preview version of Windows Vision Skills was announced, which is part of the NuGet suite package , which makes it easy for application developers to solve a whole complex of computer vision problems using a simple API set.


Figure 1 - From left to right, you see in action: Object Detector, Skeletal Detector and Emotion Recognizer.

With Windows Vision Skills:

• An application developer can use out-of-the-box WinRT APIs to add ready-made vision skills such as object detection, skeletal detection and face sentiment analysis in their Windows applications (.NET, Win32 and UWP).
• A computer vision developer can use hardware accelerated frameworks on Windows devices, packaging their solution as Vision Skill and not worrying about low-level APIs.

')
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 the on-model output of ONNX, using WinML for local output. The framework allows you to create intelligent applications using platform optimization features.

Get started now!

Play with the submitted samples or learn how to create your own Windows Vision Skills-projects using our tutorials .

Do you have an idea for a new feature or do you want to send feedback? Find us on github .