Microsoft recently launched a new face detection API to developers, but it also came up with a rather cool demo for anyone to test out. It's a website called How-Old.net that attempts to predict the age and gender of a person just by scanning a picture.
Microsoft combined a number of its products and services, including Bing and Azure, to create the website. It stated:
"We wanted to create an experience that was intelligent and fun could capture the attention of people globally, so we looked at the APIs available in the Azure Machine Learning Gallery. The gallery contains many finished intelligent services such as Face, Speech, and Vision which are part of a new suite called Project Oxford from Bing and Microsoft Research. The Face API has a demo page that uses the API to detect and extract information about faces in a photograph. We found the ability of the face API to estimate age and gender to be particularly interesting and chose this aspect of it for our project."
The site not only allow people to upload their own pictures to be scanned, it also allows them to use photos found in a search powered by Bing. The final result is, well, interesting but not necessarily accurate. Our own Derek Kessler is still a young and spry 28 years old but How-Old.net has labeled him as 41 years old when we uploaded a recent photo of him.
Microsoft says that it is striving to improve the new face detection API, so hopefully How-Old.net will offer more precise predictions over the next several months. Microsoft is adding in face detection as one of its new Windows Hello security features in Windows 10.
Source: How-Old.net, Microsoft
