Microsoft’s How-Old.net API

Microsoft's How-Old.net API - Header



Last week, as part of its Build conference, Microsoft took the time to show off many of its latest Azure-based APIs to the world. One such API, which has gained a lot of interest even within the first few hours of going live, is the company’s facial recognition software, or Project Oxford, aimed at predicting your age and gender. Via the website, How-Old.net, users can upload their selfies to the site, which will, in turn, process the image and produce results in the form of age and gender.

Microsoft's How-Old.net API - 01

Many people were originally concerned about the storage and captured details of their images, but Microsoft responded with the following comment:

“We’ve had some questions so we updated this post to be more clear. To answer the top one: No we don’t store photos, we don’t share them and we only use them to guess your age and gender. The photos are discarded from memory once we guess. While we use the terms of service very common in our industry, and similar to most other online services, we have chosen not to store or use the photos in any way other than to temporarily process them to guess your age.”

Microsoft's How-Old.net API - 02

Although the API remains quite interesting, and frustrating for some users who appear older than they are, the story behind the sudden uptake was just as fascinating. When the team originally shared the demo site for the conference, they forwarded the link to a select few, hoping to get feedback and activity from a mere 50 users, what they got back was 35,000 users, all in the space of a few hours. A single tweet in Turkey spawned the craze, as the country accounted for 29,000 of the above-mentioned population. In addition to the success in terms of numbers, the flurry of activity amongst users saw them uploading more than 210,000 images during the same time.

If you’re interested find out more about the API and facial recognition from the company, you can visit the MS blog, and Machine Learning Azure project. The company will be using the API as part of the facial recognition login system.

Written by