Subscribe now

Technology

The best image-recognition AIs are fooled by slightly rotated images

By Douglas Heaven

13 March 2019

upside down dog

When you look at it this way, the world seems odd to an algorithm

Lori Adamski Peek/Getty

TELLING a yellow taxi and a pair of binoculars apart is so easy most people could do it standing on their head. Not so for an artificial intelligence: flip the cab upside down and it sees binoculars.

This is just one of dozens of examples that show AI is a lot worse at identifying objects by sight than many people realise.

The examples, compiled by Anh Nguyen at Auburn University in Alabama, raise concerns about the real-world ability of image-recognition systems, for example…

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox. We'll also keep you up to date with New Scientist events and special offers.

Sign up

To continue reading, subscribe today with our introductory offers

Popular articles

Trending New Scientist articles

Piano Exit Overlay Banner Mobile Piano Exit Overlay Banner Desktop