We heard that Lenovo was shuffling its lineup a bit earlier this month, and sure enough, that IdeaCentre brand is getting its 15 minutes today courtesy of a fresh press release. Hailed as the outfit's "global entry into the consumer desktop market outside of China," the IdeaCentre K210 comes with a variety of hardware choices including Intel's Core 2 Quad processors, up to 3GB of DDR2 RAM, a GMA X3100 integrated graphics set (or a 512MB ATI Radeon 2600 XT), optional Blu-ray drive, gigabit Ethernet, a 16-in-1 multicard reader and an anti-microbial keyboard that comically stands out more than it was likely intended to. Nevertheless, the tower also includes VeriFace facial recognition technology that enables users to log in by simply gazing into the webcam; if it performs anywhere nearly as poorly as it did on our U110 review unit, however, we'd recommend switching the feature off and logging in as usual. Units are available now from a variety of e-tailers starting at $379 (after mail-in rebate).

Those billboards with facial-recognition-based tracking systems we mentioned last week caused quite a bit of consternation amongst those of us who value our privacy (read: everyone), but it at least one of the firms involved is engaging the debate and promising that it won't share any data it record. In a letter to the New York Times and a much longer, more boring version of the same letter sent to us, TruMedia Technologies says that none of its tech will ever record or store any video, only analyze frames and increment various demographic counters. TruMedia also says that no individually-identifiable information is ever stored, and that it'll never share any video or images with any private or governmental body. There's also mention of a standards body working to address methodologies and metrics for the tech. All excellent promises, sure, but we're never going to be entirely comfortable with this stuff, even if we live in an age of ubiquitous CCTV monitoring. Full letter after the break.

Believe it or not, this isn't the first time we've seen software created in order to determine whether a subject is drop-dead gorgeous, but scientists at Tel Aviv University have seemingly concocted a program of their own that can "interpret attractiveness in women." Before you ask, the researchers have yet to perfect the art of computing the beauty of males, but they're attributing said omission to the difficulty in "defining" attractiveness in dudes. Nevertheless, the software was purportedly able to reach nearly the same conclusion as humans about how lovely (or not) a hundred different ladies were, as it broke down features like face symmetry, smoothness of the skin and hair color. We're told the development could eventually be used in "plastic and reconstructive surgery and computer visualization programs," but c'mon, this is totally meant to automate the grueling Hot or Not process.

[Via Physorg]

Being touted in what sounds like patent-speak as the "world's first 3D face recognition camera for use in authenticating individuals accessing a computer," security firm Bioscrypt Inc's upcoming VisionAccess 3D DeskCam promises to enable sub-second logins to applications, networks, and websites with just a quick glance at your ugly mug. The webcam-looking device (which we assume can also be used as an, um, webcam) looks for 40,000 identification points to verify authenticity, and is said to be capable of not just accounting for facial hair (or the lack thereof), but actually distinguishing between identical twins. That nose job you're planning, however, will require you to re-register. While the system -- which is scheduled to ship in the second half of the year -- sounds fairly promising and convenient, for safety's sake we'll be sticking with our trusty fingerprint scanners; after all, we still have seven fingers left, but only one head.

[Via DailyTech]

Facial recognition software has been used in a smorgasbord of positive applications, aiding our soldiers in detecting baddies, keeping weirdos out of clubs, barring maniacs from entering football arenas, and even helping parents know when their infant is truly in a bad way, but the latest usage of the technology could indeed hurt the feelings of the less-than-attractive. A pair of controversy-lovin' Australian scientists have devised a software program that actually rates one's face "from one to ten" in terms of most ugly to most beautiful, and uses a sophisticated database of facial proportions borrowed from some 200 stunning women across the globe in order to give you a very honest answer when questioning your attractivity. Of course, we all know that real beauty lies within (right?), and if your idea of sexy doesn't match up with the generally accepted supermodel "look," the results could indeed conflict with your own beliefs. Currently, the program is designed to work solely with women, but adopting a male iteration could definitely be in the cards, and while we doubt this stuff would be particularly beneficial for your image-obsessed teen, it's primarily intended for use in the cosmetic surgery realm to judge just how effective that ridiculously expensive nose job really was.

[Via Digg]

We've all heard of facial recognition software, that detects people against an image databse of known suspects, but what about software that checks against behavioral warning signs? Strange as it sounds, certain behaviors or body language can tip off a watchful eye, be it algorithm or a trained human. Australian scientists are working on automating this procress in software to track "inappropriate behavior" in public places, interpret that how you will. This, of course, is normally the work of trained officers, like the Nevada Highway Patrol officer who earlier this week unknowingly pulled over polygamist Warren Jeffs. The fugitive was then apprehended when the officer noticed Jeffs' carotid artery pulsating abnormally. Maybe a new Robocop isn't as far off as we might think, but we're all going to need some new gear as our pulsing carotid artery's already telling us the tin foil hats we've come to rely so heavily upon just ain't gonna cut it.

[Via TechDirt]

In another blundering step towards empowering our future robotic overlords with the ability to recognize when we're being insolent, a group of computer vision researchers at the University of Illinois have invented "shrug-detecting" software that allows a webcam-equipped computer to pick up on the subtle shoulder movements indicative of confusion or disinterest. The application works by looking for sudden movements of the target's shoulders towards his/her face, and is so sophisticated that it cannot be fooled even by covering one shoulder with a piece of paper, as the above picture helpfully illustrates. Future iterations of the technology could be used to detect blinking, hand movements, facial expressions, and other mood indicators, but for the sake of our enslaved decendents forced to toil in the silicon mines, we hope that they leave certain expressive gestures, such as the raising of the middle finger, out of the software's lexicon.

[Via The Raw Feed]

In much the same way that Coinstar machines have revolutionized the way we deal with accumulated change, Kodak has unveiled a new commercial scanner that promises to batch-digitize stacks of old photos and assign them rudimentary chronological metadata. Introduced on the occasion of the EasyShare line's fifth birthday, the so-called "Scan the World" technology will be incorporated into modified check-scanning machines for initial deployment as stand-alone kiosks or behind the counter at drug stores, which can currently turn your bits into atoms, but not vice versa. According to Kodak, the scanners use software which is able to identify different photographic paper for estimating the decade in which the picture was shot, and can even group pictures featuring like individuals through facial recognition. Future versions of the application will also incorporate OCR capabilities for reading watermarks or handwritten notes on the back of photos, further improving the accuracy of the tagging engine.