Microsoft has unleashed another AI experiment on the web, this time hoping for better results than its rogue Tay Twitter bot.
The company launched CaptionBot.ai, which can analyse a photo in seconds and describe it.
Powered by Microsoft’s Cognitive Services, the bot looks over any images and gives rudimentary descriptions of what it can see using a Computer Vision API, an Emotion API and a Bing Image API.
This is the same base software Microsoft has used for its How Old Do I Look? system.
To actually create the captions, this system has been coupled with the language system from Tay, Microsoft’s attempt at a chat bot that was shut down after a vulnerability led to it tweeting racist and sexist remarks.
The photo captioning system is not completely accurate, but attempts to describe the person in an image, what they’re doing and their emotions in the moment. It can also recognise animals and describe landscapes,
But still needs some work:
Lol. https://t.co/CcyyDR1Vus #startrek pic.twitter.com/bIiZ1cxQYW
— BurlapJack (@burlapjack) April 14, 2016
Microsoft's image captioning tool sees through the so-called "moon landings" https://t.co/WWr7O1XeE3 H/T @robmanuel pic.twitter.com/BDd9X4KdNp
— Ralph Harrington (@ralphharrington) April 14, 2016
I'm going to crush the rebellion… but first, let me take a selfie. #captionbot pic.twitter.com/Zr6x9n0m1T
— Stephanie Melnick (@stephmelnick96) April 14, 2016