See if Microsoft can guess your age right at this fun site

 

Can a machine really learn to guess a person's age just by looking at a photo? Microsoft is taking a fun approach to this with a new website.

 

Aptly named How-Old.net, the site uses facial recognition to determine the age of a person depicted in a photo uploaded to it.

Click here to check out How-Old.net for yourself.

 

But this early, the site explained it may not get the age and gender of those in photos right, as it is still a work in progress.

 

Still, the site has proven viral, with 115,000 Facebook shares and 50,800 tweets as of Friday afternoon.

 

While some outright criticized the site's guesses, others had a more lighthearted reaction.

 

"I got mostly younger ages than I am for all pictures EXCEPT my profile picture where I'm like 19-20 sticking out a blue lollipop stained tongue.. apparently that's what 74 yr olds look like," one user said.

 

Another suggested adding a button to provide feedback if the guess was accurate.

 

A blog entry explaining the site was published April 29, Wednesday.

 

"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," said Corom Thompson and Santosh Balasubramanian, Microsoft's engineers in information management and machine learning.

 

They said 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. To make the experience more fun we used the face API alongside the Bing Search API from the Azure marketplace to create http://how-old.net," they said.

 

They said that while they initially expected 50 users for a test, in the end they got over 35,000 users "and saw the whole thing unfold in real time."

 

Within hours, they said over 35,000 users had hit the page from all over the world, 29,000 of them from Turkey.

 

They also found over half the pictures analyzed were of people who had uploaded their own images. — Joel Locsin/TJD, GMA News