Microsoft's Project Oxford has developed machine learning technology and artificial intelligence that can detect how you're feeling.
The technology is an API that can be built into applications by developers to identify emotions, recognising the way peoples' faces change as they go through a variety of feelings.
"The Emotion API takes an image as an input, and returns the confidence across a set of emotions for each face in the image, as well as bounding box for the face, using the Face API," Microsoft Oxford Project explained. "If a user has already called the Face API, they can submit the face rectangle as an optional input."
Microsoft chose to use globally-recognised expressions such as anger, contempt, disgust, fear, happiness, neutral, sadness and surprise as the basis of its research because the face tends to show these emotions in the same way, whatever the facial features.
The technology could be used by companies that want to find out how their customers react to store displays, films or food, Microsoft said. It could also be used to present certain content to people based upon their emotional state.
Other vision-based APIs the group is developing include a computer vision API that can help identify the subject of an image and flag it as inappropriate for certain age groups or tag it in a certain category and a face API that help detect certain facial features, making assumptions on factors like age, pose, gender and landmarks in the background to add location.
Project Oxford has also created language and speech APIs to encourage developers to integrate more advanced artificial intelligence into their apps. Spell check recognises slang words, brand names and misused words, while speaker recognition can identify nuances in different voices, which Microsoft said could be used as an advanced security mechanism.
"The exciting thing has been how much interest there is and how diverse the response is," said Ryan Galgon, a senior program manager within Microsoft's Technology and Research group.
