TORONTO – Everyone knows you should always tread carefully when guessing someone’s age – but it looks like Microsoft missed that memo.
The software giant’s newest analysis tool – How-Old.net – has become the latest Internet craze. The tool allows you to upload a photo of yourself and wait for the program to detect your face. It will then guess your gender and age.
Sounds innocent enough, right?
Not if Microsoft’s algorithm suspects you as being much older than you really are.
Provide How-Old.net with a well-lit, flattering photo and it usually comes up with a fairly accurate result – give or take a few years.
But, sometimes it’s hilariously wrong, which has caused many to tweet their outrageous results.
How-Old.net is powered by Face APIs, a new tool that launched this week at Microsoft’s Build 2015 developers conference. According to Microsoft, the tool is a cloud-based application program interface (API) that “provides the most advanced algorithms for face detection and recognition.”
That being said, the tool is still under development and even displays a warning under results that reads, “Sorry if we didn’t quite get the age and gender right – we are still improving this feature.”
I used several different pictures of myself to test the software and received varied results.
The first photo (a selfie I took while writing this story) told me I was 27-years-old – two years older than my current age.
I then upload my headshot (as seen on the Global News website) and it told me I looked 32-years-old.
(I think it might be time for a new headshot.)
But – unintentional insults aside – the tool has become wildly popular since its release.
“Forget Minesweeper or Solitaire — this is the best game Microsoft has bestowed upon humanity,” wrote The Verge’s Josh Lowensohn.
According to Microsoft’s blog, the team was expecting about 50 users to test the algorithm, but ended up receiving more than 35,000 users in just a few hours.
Perhaps the most entertaining way to play with #HowOldRobot is by uploading pictures of celebrities, video game characters, or well known faces (like Colonel Sanders).