Microsoft's Project Oxford Uses Algorithms to Detect Emotion in Photos
gadgetnator.com |
You can try it here, but in short, it will detect where the faces appear in a given image and then split a 1.0 score across the different emotions the face might convey, the options being anger, contempt, disgust, fear, happiness, neutral, sadness and surprise.
Some scores will be scattered between most or all of the options, whilst others might give one emotion a perfect score. I obviously have a very difficult face for this process, since basically every image of myself I put through the system came back with a broad spread of emotional readings, with 'neutral' being the most common. I'm not sure whether or not I should be offended by that.
I was really happy when this was taken, get it together, Microsoft |
Microsoft are obviously fairly proud of this tool, as they've started referring to it as 'Emotion API' and boasting of the 'world class machine-learning techniques' which make it tick. It wouldn't be a stretch to imagine that, with a little polish, this feature could work for digital marketing purposes, but if Facebook got their grubby hands on it, photo collage tools that use emotions as a centerpiece could be another potential use. For now though, it's just a curious little distraction. I've taken to putting people with characteristically weird faces through it in the hopes of breaking the system, Christopher Walken, Nicholas Cage and so forth.
Callum is a film school graduate who is now making a name for himself as a journalist and content writer. His vices include flat whites and 90s hip-hop. Follow him @CallumAtSMF
Contact us on Twitter, on Facebook, or leave your comments below. To find out about social media training or management why not take a look at our website for more info: TheSMFGroup.com
Microsoft's Project Oxford Uses Algorithms to Detect Emotion in Photos
Reviewed by Unknown
on
Wednesday, November 18, 2015
Rating: