Crave

Face recognition technology isn't perfect yet.

That's certainly clear when using the "Faces" feature that is built into the recently released iPhoto '09.

Memo to iPhoto: Former colleague Joris Evers may be a great guy, but he's not the Great One.

(Credit: Ina Fried/CNET News)

Sure, the product does reasonably well at finding your friends and family in your photo collection. Tag a few photos by name and iPhoto comes up with other suggestions, often recognizing photos that are taken years apart and with vastly different looks. Heck, iPhoto even spotted me when I was a different gender.

The science behind face recognition is complex and still evolving. In general, face recognition software looks for predictable patterns--characteristics and proportions that stay constant from one photograph to another, things like the distance between the eyes or from the eyes to the mouth.

Even with things where the science is today, having help--any help--with the tedious task of tagging photos is welcome. And iPhoto can certainly find plenty of matches in your library, even if it won't spot them all.

But the real genius part is how Apple has made the process fun, even when the results aren't perfect.

Early speech recognition was also hit or miss, but it was painful to have to scream at a computer while it constantly misunderstood what you were trying to say. With face recognition, at least as built into iPhoto, the goofs are what make it fun.

The software frequently suggested that my contemporary friends and family were actually my 80-something cousin, my 90-something great aunt, or both. iPhoto also confused Bill Gates with our friend's 3-year-old. And among the suggestions for former CNET colleague Joris Evers was a shot of Wayne Gretzky that I had taken at the Hockey Hall of Fame in Toronto.

This is me being enrolled by the Y430's Lenovo Veriface III authentication software to be a legitimate user of the computer.

(Credit: Dong Ngo/CBS Interactive)

Updated at 1:14 p.m. PST Friday, December 5 with comment from Lenovo.

Editor's note: CNET editor and Crave contributor Dong Ngo is spending the month of December in his homeland of Vietnam and plans to file occasional dispatches chronicling his impressions of how technology has permeated the culture there. Click here for more of Dong's stories from abroad.

HANOI, Vietnam--Regardless of what some people seem to think, we Asians do not all look the same. But according to the current face recognition algorithm used in laptops, our faces are all about as flat as a piece of paper.

That's according to BKIS, the Vietnamese Internetwork Security Center that makes the antivirus software I mentioned in a blog post Monday. At a press conference here Tuesday, the company demonstrated vulnerabilities in laptops' face recognition-based authentication mechanisms that let anyone log in to a computer easily with a "special" photo of the legit owner, even at the highest authentication level.

Using your face as the password to log in to a computer--an alternative to the fingerprint method or the traditional username and password--marks a new trend found in laptops from Lenovo, Asus, and Toshiba. As far as I know, only these three vendors currently offer this technology in their laptops. These computers come with a built-in Webcam that's used to capture and analyze faces.

I've been impressed by this new way to log in and have found it to be so much more convenient than the fingerprint reader of my Dell XPS 1330. The finger scanner is a pain when my finger is wet or dirty. Unfortunately, on Tuesday I discovered that this new and exciting technology may not be such an effective security measure.

I participated in a demonstration on a Lenovo Y430, running Windows Vista, and here's how it panned out:

MONTEREY, Calif.--Get ready for a new era in which your camera knows not just when you took a picture but who's in it, too.

Many cameras today can detect the faces of those being photographed, which is handy for guiding the camera to set its exposure, focus, and color balance properly. But the more difficult challenge of face recognition is more useful after the photo has been taken.

University of California-San Diego researchers have turned expression-recognition technology into an art exhibit showing the increasingly strained efforts by models to maintain a chipper smile for more than an hour. A buzzer goes off when a waning smile sends a monitor into the red zone.

(Credit: Stephen Shankland/CNET Networks)

That's because of a concept called autotagging, one of a number of technologies that make digital photography qualitatively different from the film photography of the past.

Tags of descriptive data can be attached to digital photos, and they help people find and organize pictures. The only problem is that tagging your photos, today a laborious manual task, is like eating your vegetables. It's good for you but a lot of people don't like it.

With autotagging, the camera attaches tags as the pictures are taken. Today, cameras embed timestamps in photos, which makes it possible to sift through pictures by date. But be honest here--how reliably can you remember exactly when you took that picture of your darling daughter a year or two ago that you'd like to e-mail to her grandparents? Being able to screen for photos only of a particular person could dramatically speed up the search process.

Face recognition requires computational horsepower that is hard to fit into the confines of a digital camera, but one company likely to help make it a reality is Fotonation, which already supplies face-detection software for dozens of camera models from Samsung, Pentax, and others.

The computational challenge is reduced by the fact that most folks tend to photograph the same set of 25 or 30 people, Eric Zarakov, Fotonation's vice president of marketing, said in an interview here at the 6sight digital imaging conference. A camera could be "trained" to recognize just those particular people.

He wouldn't comment on whether Fotonation plans to sell such software to camera makers, but it sure looks likely. "We're looking at a lot of stuff. That would be a natural extension" of today's product lines, Zarakov said.

One camera maker willing to mention its interest in autotagging is Panasonic. "A lot of thought is going into how to tag photos so you can retrieve them at a moment's notice," said Alex Fried, national marketing manager for imaging at Panasonic's Consumer Electronics Co. But he wouldn't go into specifics: "There are things we have in the works that will help benefit consumers going forward."

And faces aren't the only aspect of autotagging that's likely to show up in cameras. Location, too, is another useful attribute that can be attached to photos through a process called geotagging. Geotagging can be used both to look for photos whose location you know and to figure out what exactly is in a photo you already have at hand.

Today, geotagging is generally a laborious manual task that requires geographic data to be merged with photos after the fact using a computer. But more power-efficient approaches will lead to in-camera GPS systems that will enable automatic geotagging, predicted Kanwar Chadha, founder of GPS chip designer SiRF Technology.

"A location stamp is much more important than a time stamp in most cases. A year down the road, you have no idea where those pictures were taken and no way to search for location," Chadha said.

Face recognition is an area of active research and some commercialization. Start-up Riya is working on technology to search through online photo albums to try to identify individuals. Polar Rose is trying to improve recognition by generating 3D models of faces. And 3VR wants to apply face recognition to what's become a highly lucrative market, security.

Software from University of California-San Diego researchers, shown here at the 6sight digital imaging conference, can identify facial expressions. This shot shows the nose-wrinkling detector in action, which Marian Stewart Bartlett believes could be useful for market researchers.

(Credit: Stephen Shankland/CNET Networks)

At the 6sight conference, Marian Stewart Bartlett showed results of her research into not just face detection, but expression detection. Her work at the Machine Perception Lab at the University of California-San Diego lets a computer monitor 30 of the 46 codified components of facial expressions. That includes movements such as raised eyebrows and wrinkled noses.

In the demonstration, software tracked Stewart's face from a video camera and recorded expression parameters. Analyzing the data, the computer can draw conclusions about people. For example, when comparing a video of a man's face as he experienced actual pain from immersing his hand in cold water to another in which he faked the pain, people had about an even chance guessing which showed the authentic pain. The computer, though, had 72 percent accuracy, she said.

That level of sophistication is beyond a camera's abilities today, requiring a full-fledged computer run by people with Ph.D. degrees. But particularly given that Sony already has introduced a camera with smile detection, it's not hard to imagine a day when your photos could also some day be tagged "delighted" or "disgusted," too.

(Credit: Lenovo)

The eagle-eyed crew over at NotebookReview tipped us off to the appearance of a new laptop on Lenovo's U.S. site. Part of the Lenovo 3000 family, the 14.1-inch Y410 was announced in the Asia markets earlier this year, but it arrived in the States without even a press release. Curious, considering the Y410 represents the company's first foray into the consumer--also known as "home/home office"--market here.

Though its boxy silver case is hardly a departure from the conservative look of the Lenovo 3000 line, the Y410 includes entertainment-oriented features you wouldn't find on a business machine, including Dolby Home Theater audio with a subwoofer, the ability to play CDs without booting the system, and a media player called Shuttle Center. The laptop also is the first we've seen to pair a built-in 1.3-megapixel Webcam with VeriFace software to provide biometric security via face recognition.

Another first for Lenovo, which has been slowly growing its presence in retail: the Y410 is available only at retail stores--currently, Office Depot, Micro Center, and Staples--and not on Lenovo's site. Each store has a slightly different configuration, the least expensive being Staples' $700 version, with a 1.46GHz Pentium Dual Core processor and 1GB of memory. Office Depot, meanwhile, seems to be offering the top of the Y410 line, with a 1.66GHz Intel Core 2 Duo T5450 processor and 2GB of 667MHz RAM for $950.

All 5.2-pound Y410 models feature a 14.1-inch display (1,280x800 resolution), integrated Intel X3100 graphics, a 160GB hard drive spinning at 5,400rpm, a built-in DVD burner, and a six-cell battery that the company claims will last up to 4 hours.

Pricewise, the Lenovo 3000 Y410 is competitive with similarly equipped systems, such as the HP Pavilion dv2500t and the Dell Inspiron 1420. What remains to be seen is whether the subdued Y410 can win over consumers who've come to equate the Lenovo brand with work.