Under the name of Project Oxford, Microsoft has made available a set of RESTful APIs that aim to make it possible for developers to build apps that feature face recognition, speech processing, and other machine learning algorithms. Part of the Azure portfolio, the new APIs are currently in beta and free to use up to 5,000 call per month.
Project Oxford, which provides a live demo, includes four main components:
-
Face recognition, which can be used to recognize faces in photos and verify whether two faces belongs to the same person. Face recognition, according to Microsoft, could be used to power face authentication.
-
Speech processing, which provides speech-to-text and text-to-speech translation.
-
Visual tools, which can be used to analyze images and identify inappropriate content in it, or detect and understand text, and even classify visual content, e.g., images of beaches, animals, food, etc.
-
Language Understanding Intelligent Service (LUIS), which promises to enable applications to understand users' intent when they say or type a sentence in natural language. This last API is currently only available on invitation.
Besides RESTful APIs, Project Oxford also provides SDKs to make it easier to integrate their services on both .Net and the Android platforms. A Speed SDK is additionally provided for iOS.
For each service, Project Oxford includes detailed documentation that will guide developers through all the steps from subscribing to a service to integrating it into a basic app.
As TechCrunch reports, Microsoft used to offer a similar set of APIs under the Bing moniker, which, according to Ryan Galgon, a senior program manager on the Oxford project at Microsoft Technology and Research, were more oriented to the desktop experience.