Microsoft Publishes API for Emotion Recognition

Published on November 18, 2015 by

Microsoft has published an API for┬árecognizing emotions in images by using machine learning. The tool is able to detect various emotions in an image by analyzing facial expressions. It then calculates scores for these emotions and returns these results in the JSON format. This tool is part of Microsoft’s Project Oxford, but is still experimental, and the results are therefore not always accurate.

Below is an example of an analysis made by the tool.

Emotion Recognition

This emotion recognition tool is yet another example of the increasing popularity and maturity of machine learning, and all of the large IT companies are investing and researching heavily in machine learning. While the cloud providers continue to make machine learning available to their customers, Google also makes heavy use of machine learning for yielding search results.

The tool is freely available and a live demo can be found here, as well as API documentation and an SDK.

Author avatar
Bo Andersen

About the Author

I am a back-end web developer with a passion for open source technologies. I have been a PHP developer for many years, and also have experience with Java and Spring Framework. I currently work full time as a lead developer. Apart from that, I also spend time on making online courses, so be sure to check those out!

One comment on »Microsoft Publishes API for Emotion Recognition«

  1. Hasee

    How do you calculate the probability value for Emotion Recognition ?

Leave a Reply

Your e-mail address will not be published.