The goal of autofocus is to make something in the picture come out sharp. But if you're taking a photo of people, it's not their hands you want in focus. Recently, camera makers have been adding the ability to detect faces in a scene, track them if they move, and optimize both focus and exposure to make everyone look their best. But not all face-detection systems are equal, as I discovered after testing several compact cameras
on patient friends who posed by indoor light, as well as on passersby rushing through Times Square.
How it Works
All face-detecting cameras compare the scene before them to a built-in library of features derived from images of real people, such as the distances between eyes, patterns of light and shadow, and skin colors. So far, no models can identify a face in profile, and they don't function well in low light, such as in bars or candlelit rooms. But they're not easily fooled: In our tests, none were thrown off by variations in skin tone or by accessories like eyeglasses.
Face-Tracking Face-Off
![]() |
Fujifilm Finepix F40fd |
![]() |
Sony Cyber-shot DSC-W80 |
![]() |
Nikon Coolpix S200 |
Stay up to date on the latest news of the future of science and technology from your iPhone with full articles, images and offline viewing
Featuring every article from the magazine and website, plus links from around the Web. Also see our PopSci DIY feed
Share links with friends, comment on stories and more
In our December issue, Popular Science names the 100 best innovations of the year: bombproof wallpaper, self-parking cars, the fastest helicopter, and 97 more. Plus inventor profiles and videos.
Check out the best of what's new here.