Sign In

Communications of the ACM


Seeing More Clearly

A young boy holding a baseball bat

A computer at Stanford described this photo: "A young boy holding a baseball bat."


The photo shows a baby, dressed in a striped shirt and denim overalls, staring intently at the toothbrush he is grasping in his left hand while he pokes at it with his right. The caption underneath reads, "A young boy is holding a baseball bat."

The computer at Stanford University in California that generated that description failed in this case, but in others its captions were much more accurate, if not terribly exciting. The phrases "black and white dog jumps over bar," "little girl is eating piece of cake," and "baseball player is throwing ball in game" are all correct characterizations of the photos in question. Even if it occasionally mistakes a toothbrush for a baseball bat, or a ferret for a cat, the computer today can do a much better job of explaining what is happening in a photograph than it could even a couple of years ago. The field of computer understanding of images has made remarkable progress in the last few years.


No entries found

Log in to Read the Full Article

Sign In

Sign in using your ACM Web Account username and password to access premium content if you are an ACM member, Communications subscriber or Digital Library subscriber.

Need Access?

Please select one of the options below for access to premium content and features.

Create a Web Account

If you are already an ACM member, Communications subscriber, or Digital Library subscriber, please set up a web account to access premium content on this site.

Join the ACM

Become a member to take full advantage of ACM's outstanding computing information resources, networking opportunities, and other benefits.

Subscribe to Communications of the ACM Magazine

Get full access to 50+ years of CACM content and receive the print version of the magazine monthly.

Purchase the Article

Non-members can purchase this article or a copy of the magazine in which it appears.