Available in preview, Windows Vision Skills is a suite of tools that allow AI-powered video and photo analytics. Currently there are three skills included in preview: Object Detector, Skeletal Detector, and Emotion Recognizer. As this is an ongoing development, expect more skills to be added as the tool moves to general release. “Implementing and integrating efficient machine learning and computer vision solutions is a hard task for developers. The industry is moving at a fast pace, and the amount of custom-tailored solutions coming out makes it strenuous for application developers to keep up,” wrote Microsoft developer writer Eliot Cowley in a blog post this week. “The Windows Vision Skills framework is meant to make it easier to utilize computer vision. It standardizes the way computer vision modules are put to use within a Windows application, running on the local device.” Skills are presented as code that are modular, allowing developers to add the skills they want to their solutions. Skills can be output into any Win32, .NET, and Universal Windows Platform (UWP) applications.
App Integration
This is achieved through WinRT APIs that are available in Windows Visions Skills packages. Importantly, Microsoft says no previous knowledge of machine learning of computer vision is needed to work with the APIs. Many developers will already have machine learning solutions up and running. Windows Visions Skills can tap straight into them. Furthermore, skills can be combined together in an app to handle different scenarios. “Skills are strongly versioned to ease iteration without breaking existing applications,” said Cowley, “[and they’re] easy to ingest, easy to update, and they preserve intellectual property through licensing.”
