facerecognition
Latest
Face.com kills developer APIs and Klik app three weeks after Facebook acquisition
A ripple went through Face.com's developer community three weeks ago when the company was acquired by Facebook. After all, what earthly reason would the social network have for continuing third-party developer support of the product? None, as it turns out -- API support for the firm's mug recognition software will be dropped in early August, and its iPhone app, Klik, is now gone from the App Store. Despite recent assurances to the contrary (pictured above) Face.com pulled the plug in order to devote its resources to Zuckerberg and Co., according to an email it sent to developers. Naturally, the sudden reversal has inflamed that group, with prominent members tweeting language like "boycotting" and "months of work wasted." There's a sliver of hope, however, for forlorn developers -- at least one member of the community says he's been granted an API extension through October. In the meantime, developers will likely be venting -- and won't even be able to track that rollercoaster of emotions anymore.
Google patent filing would identify faces in videos, spot the You in YouTube
Face detection is a common sight in still photography, but it's a rarity in video outside of certain research projects. Google may be keen to take some of the mystery out of those clips through a just-published patent application: its technique uses video frames to generate clusters of face representations that are attached to a given person. By knowing what a subject looks like from various angles, Google could then attach a name to a face whenever it shows up in a clip, even at different angles and in strange lighting conditions. The most obvious purpose would be to give YouTube viewers a Flickr-like option to tag people in videos, but it could also be used to spot people in augmented reality apps and get their details -- imagine never being at a loss for information about a new friend as long as you're wearing Project Glass. As a patent, it's not a definitive roadmap for where Google is going with any of its properties, but it could be a clue as to the search giant's thinking. Don't be surprised if YouTube can eventually prove that a Google+ friend really did streak across the stage at a concert.
Face.com acquired by Facebook for an estimated $80 million+, facial tagging clearly at the forefront
Facebook already dropped the "the," so why not oversimplify and drop the "book," too? All jesting aside, Facebook is continuing its recent buying spree with the acquisition of Face.com for an estimated $80 - $100 million. The Israeli-based startup is being entirely scooped up by Zuckerberg's social network -- talent and technology included -- and it's fairly obvious that the company's heralded facial recognition IP is what Facebook is truly after. To date, Facebook's desktop tagging recognition is ho hum at best, and it's practically an afterthought on the mobile front; 'course, with Camera• now being released, it's high time the company got serious about tagging on the go. For those wondering, Face's blog post on the matter seems to make clear that third-parties currently using its API will continue to be supported, and while there aren't specific plans being laid out, we're told that the "next steps are going to be exciting for all of us." In related news, it's tremendously unlikely that Barnes & Noble lets go of book.com in order to give Facebook the pleasure of owning both ends of the URL spectrum.
Wall-mounted interactive robot mimics emotions, follows you around, wants to be friends (video)
Not every robot is here to make our food, clean our floors or perform interstellar maintenance for us. Some automatons are there to simply be admired... or in the case of GIA (Gestural Interactive Automaton), to admire us. GIA's a robotic sculpture created by Daniel Jay Bertner that is essentially a projector, projection sphere and a webcam attached to a trio of servo-controlled articulating arms. A human face is projected on the sphere, which follows around folks who view it and changes its facial expression according to viewer reactions. Why? In order to "emulate and socially engage" them and facilitate a better understanding between man and machine, of course. The magic happens through open source motion tracking and facial recognition software, but you don't have to take our word for it -- see for yourself in the video after the break.
Webcam programmed to capture your face while playing Xbox: gauges your excitement, graphs ennui
Sometimes, those Modern Warfare sessions really take their toll. Now, there is a way to measure the emotional rollercoaster you're subjecting yourself to when you login for those regular gaming stints. Dale Lane decided to hook up the webcam above his main TV to grab a shot of his face every 15 seconds. This then wings its way to the Face.com API, which calculates all sorts of information about the image and sends it back to Dale, who uses a Python script to cook it into these graphs. This one measures his early evening session playing Blur on Xbox Live. Yeah, red means angry.
Samsung tweaking Face Unlock to require blinking, smiling still optional
Still paranoid about a friend sneaking past your four-dot-oh facial security and revealing all your little secrets? Worry no more, as Sammy's got a solution for you. The new feature is stuffed inside the tasty ICS being delivered now to global Galaxy S IIs, adding the need to blink in order to bypass the Face Unlock screen. Aside from the eyelash-flashing bit included in the upgrade, Samsung's Product Planning Team says they've also added Photo Editor, Beta Font, Snapshot and a novel S Go Launcher Pro. You can check out the full interview with Samsung's whiz-squad at the source below.
Face-recognizing billboard ad identifies gender: no boys allowed (video)
A new face recognition ad will only reveal its full contents to women. It uses a "high-definition" camera to scan people's faces, detecting their gender with an apparent 90 percent success rate. The charity, Plan UK, is looking to raise funds to sponsor education for girls living in developing countries; the outdoor display will run the full advert for female viewers, while men will get a brief glimpse followed by directions to the charity's website. It's aiming to demonstrate the limits put on young women in some countries -- and is a pretty admirable use of facial recognition technology. Well, it's not withholding pudding from minors. Check the bus display in action on the streets of London right after the break.
Taking next-gen augmented reality for an ARM-powered walk around the block
We know what you're thinking, because we initially thought it too, but this isn't your average AR. With the help of chip designer ARM, a number of developers are building a new type of augmented reality that is altogether more powerful than the usual sprite-on-a-surface routine. Instead of requiring well-lit, artificial and often indoor surfaces and markers, this new technology sucks every ounce of juice from a smartphone's processor in order to recognize, track and augment real-world 3D objects like people and buildings. It's still at an early stage and far from being practical, but the exclusive videos after the break ought to prove that this approach has potential. In fact, it's probably what augmented reality ought to have been in the first place. Read on for more.
How I Met Your Robot Mother: a Qbo 'First' (video)
Is consciousness programmable? Do robots feel? Would Kubrick have approved of Spielberg's handling of AI? While you wrap your mind around those conundrums, set aside a bit of free grey matter to soak in another Qbo milestone. When last we left the little bot, it was just coming to terms with its place in the grand scheme of things and recognizing its reflection. Since, robotic hangers-on and the geeks that love'em have been pelting The Corpora (the brains behind the operation) with questions pertaining to the self-awareness of this artificially intelligent machine. The outfit's reply? A Qbo meet-cute with a "female" member of the automated species that highlights the droid's understanding of individuality. It's a far cry from a Lady and the Tramp-style nose nuzzle, but these bots don't have to touch -- a random series of nasal flashes serve to indicate their distinctiveness and, once that's done, polite flirtation ensues. Don't believe us? You can see the sparks of android love for yourself in the video after the break.
Apple going after face detection patent on iOS
Patently Apple has a report on Apple's latest just-revealed patent application for a system that runs on iOS devices that would recognize user faces and their local presence (originally filed in Q2 of 2010, released by the USPTO this week). It sounds like the old Minority Report gag, where your iOS device would monitor its surrounding environment for faces, and when one gets close enough and is identified as yours, the device would unlock and open up for use. Apple's patent also mentions algorithms for identifying specific features of the face, such as the eyes and the tip of the nose, and even methods to deal with low-light situations and other criteria which would make it hard to do the identification. Update: Yes, as commenters and other sites point out, the Galaxy Nexus and other Android 4.0 Ice Cream Sandwich phones (if you can find any) include a Face Unlock feature. They were introduced this fall; Apple's patent application is from 18 months ago. Whether Apple's patent will be granted or not, and whether that impacts Google's feature, is yet to be seen. Sounds like fascinating stuff. Of course, you might worry about security while doing something like this (could it be fooled with a picture, do you think?), but then again, iOS already offers different levels of security -- some people don't use the unlock code at all on their devices anyway. And a system like this would be more than just a handy login feature -- the software also could be used to display personal information, check a person's mood, or even figure out whether the user is paying attention for not. Those stats, specifically, would probably make for very interesting reading for any developers out there. As with all Apple patents, this just shows what they're kicking around at Cupertino, not actual technology we'll be guaranteed to see on any devices in the future. But it would be cool -- hopefully Apple will work this kind of thing out, and maybe in iOS 7, we'll see faces put to a whole new use.
Apple applies for facial recognition patent, wants to let iDevices get to know you better
Your momma always said your handsome mug would take you places. Now it might allow you to access your iPad. An Apple patent application released today describes a facial recognition system that requires minimal computing power, and works whether you're indoors or out -- we don't use our tablets and phones in a photo booth, after all. The technology works by comparing a current image of your mug to a reference model user profile made using "high information" portions of the human face, like eyes and mouths. Translation: it'll take a picture, compare it against the pictures associated with various user accounts on the device and decide if the two images are similar enough to grant you access. Because this is just an application, it's safe to say we won't be seeing this kind of facial recognition in iOS anytime soon, but let's hope it works better than the ICS version if it does. Update: An important thing to note is that Apple applied for this patent long before Android's Face Unlock debuted a few months back. The paperwork was first submitted on June 29th, 2010 -- it's just now being disclosed to the public.
Kraft vending machine teases children with adult-only pudding dispenser (video)
We've seen odd and law-swerving vending machines before, but none as meanspirited as Kraft's collaboration with Intel that only gives pudding samples to adults. The unimaginatively titled iSample denies the youthful its sweet nectar by taking a facial scan and determining dessert deservedness based on biometric data, like how far apart your facial features are. Part experiment, part publicity stunt, Intel is trying out technologies that could recommend products based on age. The company also claims it may retrofit the technology into existing machines to let companies study who's buying its products; Kraft is clearly in it just to deny children some pudding. To see if you have spent enough time at the fountain of youth, head down to Chicago's Shedd Aquarium or New York's South Street Seaport, and take your place in the line of parents ordering one for their progeny. Check the promo video after the break to see the machine wiping disappointment all over the kids' little faces.
Qbo robot looks in a mirror, learns who he is (video)
A robot equipped with stereoscopic vision and some object and facial recognition programs opens up a whole number of different possibilities, but few quite as interesting as what happens when you place said robot in front of a mirror. It took a bit of guidance (and no doubt a bit of prep), but the open source Qbo robot was quickly able to both recognize and learn to identify himself when he was recently placed in just such a situation. See what happened after the break. Update: The Corpora, the company behind Qbo, has now added a more detailed explanation about exactly what is happening here on its blog.
Android Ice Cream Sandwich adds Face Unlock feature
There's no shortage of new features in Ice Cream Sandwich, but one sure to attract a lot of attention is Face Unlock. That, as you can probably surmise, lets you unlock your phone through facial recognition instead of a password -- hardly a new idea, but a first for Google. Unfortunately, the demo didn't go quite as planned during the keynote -- locking out Google's Matias Duarte -- but we'll be sure to give it a go ourselves and report back.
Face detection API found in iOS 5 (Updated)
9to5 Mac has found references to face detection APIs in the current developer build of iOS 5. The iOS 5-exclusive APIs include CIFaceFeature for identifying a the mouth and eyes in an image of a face. Additionally, CIDetector is a resource within the OS meant to process images for the purposes of face detection. Further iOS spelunking turned up hasLeftEyePosition, hasRightEyePosition, hasMouthPosition, leftEyePosition, rightEyePosition and mouthPosition. Either Apple is building a Cylon Resurrection Ship or iOS 5 will offer some cool face detection options to developers. In either case, it seems Apple's recent purchase of Polar Rose, which specialized in face recognition, is about to pay off. Update: Face detection was announced as part of iOS 5. It's a fully documented API that developers can use immediately when iOS 5 launches. That is to say, it's not a surprise, at least to some developers.
Google working on a face recognition app that leads to your personal info? (update: Google says 'no')
Before we all get in a huff about this, Google has been very eager to point out that the facial recognition app it's developing will work on a strictly opt-in basis. That means if you don't want it to scan all of Facebook, Flickr and the rest of Google's vast hoards of internet knowledge to find you, identify you, and collate your name, phone number and email address into a handy data sheet, it won't. Okay? So relax now, everything's fine. Seriously though, Google's latest research venture sounds like a dashing stride into a minefield of privacy concerns as it aims to use people's faces to instantly identify them and provide any salient info about them. Project leader Hartmut Neven, whose company Neven Vision was gobbled up by Google in 2006, says the team is being very cautious in how it addresses people's rather apt apprehension, but he insists there's actually great value in having a face-recognizing and data-mining app. Great value for the app's user, perhaps, but we'd rather just stick to business cards, if you ask us. Update: Google has reached out to clarify that there are no plans to introduce functionality of this sort yet, not without "a strong privacy model in place." More importantly, however, the linking of facial recognition to personal data is described as "inventions of the reporter" rather than something the company's actively pursuing.
Student thwarts face detection software with 'CV Dazzle' makeup
Not interested in having yourself automatically identified in photos across the internet? Then you might want to take a cue from Adam Ant (or Blade Runner's Pris, if you prefer), as Adam Harvey, a student in NYU's Interactive Telecommunication Program, has discovered that some over the top face makeup applied in just the right way can thwart most facial recognition software. Dubbed CV Dazzle (after the Dazzle camouflage used in World War I), the makeup works simply by enhancing areas of the face that you otherwise wouldn't ordinarily enhance -- so instead of applying the makeup around your eyes, you'd apply some on your cheeks and effectively "invert" that area. According to Harvey, that method is effective at blocking the face recognition used by Facebook, Picasa and Flickr -- and it doesn't simply cause some mild confusion, it actually prevents the software from detecting any face at all. Head on past the break for a quick video.
Microsoft's OneVision Video Recognizer can detect, identify, and track your face on video... so smile!
Here's your classic case of "just because you can, doesn't mean you should." Microsoft's Innovation Labs have just demonstrated a OneVision Video Recognizer algorithm that's powerful enough to perform face detection duties on a running video feed. It can recognize and track humanoid visages even while they're moving, accept tags that allow auto-identification of people as they enter the frame, and can ultimately lead to some highly sophisticated video editing and indexing via its automated information gathering. Of course, it's that very ease with which it can keep a watchful eye on everyone that has us feeling uneasy right now, but what are you gonna do? Watch the video after the break, that's what.
PALRO the robot gets upgraded to 2.0, gets improved face & body tracking, is as cute as ever (video)
Oh PALRO, you'd already won our hearts with that dirty dancing routine you learned over the summer, and heaven knows you're cute as a button. Now, though, you have the brains to match those looks. Fujisoft has upgraded PALRO's software to version 2.0, which comes with some impressive face, body, and object tracking. The little guy can now identify a face and track it even if someone turns their head, and likewise can identify a person's body at a distance while walking through a crowded room. With a quick scan of its dome-shaped head PALRO can locate all the objects in a room and, when told to walk to one, will start swinging its arms and strut right to it, dodging wayward keyboards and mice along the way. It's as impressive as it is adorable, and while PALRO still isn't available for sale to the world at large, a price of roughly $3,300 makes means he's well out of our league anyway.
Ubuntu prototype uses face recognition to intelligently move UI elements (video)
(function() { var s = document.createElement('SCRIPT'), s1 = document.getElementsByTagName('SCRIPT')[0]; s.type = 'text/javascript'; s.async = true; s.src = 'http://widgets.digg.com/buttons.js'; s1.parentNode.insertBefore(s, s1); })(); Digg Not that we haven't seen mock-ups before for systems using webcams to intelligently move user interface elements, but it's another thing entirely for a company to make a public proclamation that it's tinkering with implementing something of the sort into a future build of its OS. Over at the Canonical design blog, one Christian Giordano has revealed that the company is in the early stages of creating new ways to interact with Ubuntu, primarily by using proximity and orientation sensors in order to have one's PC react based on how they're sitting, where they're sitting and where their eyes / head are at. For instance -- once a user fires up a video and leans back, said video would automatically go into fullscreen mode. Similarly, if a user walked away to grab some coffee and a notification appeared, that notification would be displayed at fullscreen so that he / she could read it from faraway. There's no mention just yet on when the company plans to actually bring these ideas to end-users, but the video embedded after the break makes us long for "sooner" rather than "later."
