facerecognition
Latest
Facebook adds face detection, still can't identify books
Over 100 million photos are uploaded to Facebook every day, making the social networking site something of a clearinghouse for random holiday snaps. Of course, those holiday snaps quite often contain people, and its in tagging those people that the whole process of adding photos to Facebook slows down a bit -- finding faces, drawing boxes, typing names, etc. Those first two steps are now in the process of being automated thanks to recent Facebook acquisition Divvyshot. Facebook will now identify faces in your photos after you upload them, automatically, just like any 'ol cheap compact shooter can do. Sadly it won't identify who that face is yet (you still need to type in a name), but this simple addition should make tagging much, much easier. However, we're still waiting for Google Street View's auto face blurring technology to make an appearance before we start uploading the greatest moments from our last vacation.
Microsoft updating Live app suite, declares Windows 'better than Mac for photos, hands down'
Looks like it's blowhard season up in Redmond these days, as the latest word from Microsoft on its Live Essentials suite of apps has been accompanied by the brash pronouncement that it's now markedly superior to Apple's efforts in Mac OS X -- at least when it comes to photos. This verdict was delivered by Brian Hall, General Manager for Windows Live, and is backed by a laundry list of new features we can expect by the holiday season of this year. Windows Live Photo Gallery and Movie Maker will soon be able to link up directly to sites like Flickr, Facebook and YouTube -- which will allow for painless uploads as well as pulling in any additional tagging done on Facebook. New photo stitching and retouching abilities, along with face recognition (rather than mere detection) are also being touted, but the ultimate arbiter of the new software's utility will obviously be the real hands-on experience for users. We shouldn't have to wait too long for that, as a beta version of the freely downloadable (on Vista and 7, XP holdouts are no longer being served) suite should be making the rounds in the coming weeks.
Harvard and MIT researchers working to simulate the visual cortex to give computers true sight
It sounds like a daunting task, but some researchers at Harvard and MIT have banded together to basically "reverse engineer" the human brain's ability to process visual data into usable information. However, instead of testing one processing model at a time, they're using a screening technique borrowed from molecular biology to test a range of thousands of models up against particular object recognition tasks. To get the computational juice to accomplish this feat, they've been relying heavily on GPUs, saying the off-the-shelf parallel computing setup they've got gives them hundred-fold speed improvements over conventional methods. So far they claim their results are besting "state-of-the-art computer vision systems" (which, if iPhoto's skills are any indication, wouldn't take much), and they hope to not only improve tasks such as face recognition, object recognition and gesture tracking, but also to apply their knowledge back into a better understanding of the brain's mysterious machinations. A delicious cycle! There's a video overview of their approach after the break. [Thanks, David]
Sony Ericsson XPERIA X10 announced, we go hands-on
The first Android device from Sony Ericsson may have undergone an upgrade in the naming department, jumping from X3 all the way to XPERIA X10 (probably to avoid confusion with Nokia's X3 handset), but what lies under the hood is reassuringly in line with what we've been hearing. That is to say, a 1GHz Snapdragon chip from Qualcomm, wide 4-inch capacitive touch display, 8.1 megapixel camera with LED flash, and a thoroughly tricked out Android skin named Rachael. Sony Ericsson stressed to us the symbiotic importance of both the new flagship device and "open OS" UI -- the X10 was presented as the patriarch of a whole new family of handsets, which we can expect to see in the first half of 2010, all sporting the beauty of Rachael and perhaps helping to bridge the gap between featurephones and, well, more advanced featurephones. So don't be shy, come along past the break to see our uncensored first impressions of both, along with hands-on video and pictures. %Gallery-77045%
Video: Sony's Vision Library for PlayStation Eye recognizes faces, creates nightmarish human-cow hybrids
What's this, another fun tech demo from Sony? Just a few days ago we got a glimpse of the PS3VR library, which allows seamless zooming from far away to very, very close indeed. The company also showed off voice recognition tech and it's now applying the same idea to the PlayStation Eye, fulfilling earlier promises of advanced facial recognition for the PS3. It's called the Vision Library and, once a face has been analyzed, the machine can tell it apart from others, determine orientation, identify gender, tell what expression that face is... expressing, and then superimpose some big-eyed anime head right on top of it real-time. We fear this might take some of the fun out of cosplay night, but could make life rather more interesting for freaks with bovine fetishes. See for yourself after the break.
ALSOK unveils its giant, ultra-cute and friendly security bot, An9-PR
If ALSOK's latest security / guidance robot looks a bit familiar -- well, we've seen his kind before. The company's latest offering - the An9-PR is an update of its previous bot -- the better-named Reborg Q. The An9-PR is a multi-tasker, meant for showroom floors and malls, where it can display advertisements, directions to the restroom, and missing children alerts on any of its three touchscreen LCDS, and it's got WiFi and face recognition capabilities, making him a decent security guard, too! The robot weigh about 440 pounds, and is on four wheels to make it easier to move. The An9-PR will apparently go on sale in Japan starting in March of 2010, for about $150,000. There's another shot of this cutie after the break. [Via Engadget Chinese]
Apple dreaming of object identification, new messaging UI in iPhone OS patent
Seriously Apple, what's up with the patent application bender? Over the past week, we've seen a whole gaggle of new apps, though the latest few just might be the most intriguing. In essence, Apple engineers have outlined plans to integrate object recognition, face detection / recognition, a text message filter (for the parents, you know) and a new, smarter messaging interface that could remind you of unread messages before allowing you to make a call and spout off unnecessarily. Moreover, we're told of a new voice output selection that could enable Oprah or Cookie Monster to read your turn-by-turn directions, bedtime stories or recipes. Suddenly, iPhone OS 3.0 feels so... antediluvian.[Via Unwired View]Read - Unread messages applicationRead - New messaging interface applicationRead - Face detection application
Sony Ericsson's facial recognition patent plays the perfect song to complement your mood
We don't expect this to be indicative of any near-term projects for the now financially hindered phone maker, but one of Sony Ericsson's recently unearthed patents paves the way for some interesting uses. From what we gather, while listening to music on your device, a picture of your face would be taken. That image would then be run through software that interprets your mood, and an appropriate next song based on those emotions would be picked -- so much for the art of mixtapes. Presumably, it'd also require a phone or device with a camera mounted on the same side as the screen, so unless mobile video conferencing takes off in a huge way, we can't see people paying extra for a phone or device with this configuration. And if you just got dumped over SMS, we hope it doesn't intepret those tears as a good time to play that Damien Rice song you two fell in love with. Hit up the read link for the full patent details. [Via Slash Gear]
Video: iHouse SmartFaucet with face recognition is more smug than smart
Ready for the ultimate in convergence overkill? Meet the SmartFaucet from iHouse; a tap with built-in face recognition technology that automatically adjusts the water pressure and temperature to your preferred settings. The touchscreen display even features widgets for at-a-glance access to eMail, appointments, and the outside temperature while LEDs illuminate the flow with temperature matching colors. iHouse's Fadec (pictured after the break) also adds face recognition to a 2.8-inch in-house remote control. That little trick allows the remote to respond to pre-programmed scenes (think AC, lighting, audio) customized by inhabitant. Too much? Never.[Via BornRich]
iPhoto '09 uses face detection package from Omron
An intrepid tipster emailed us late yesterday, and described an interesting challenge: He figured that if Apple didn't develop iPhoto's face recognition technology themselves, who did? He disassembled the app using OTX, a developer tool based on Apple's otool, and found the areas of the software related to facial recognition. There, the string "OKAO" appeared, including in the "FaceRecognitionManager" object. OKAO Vision is a product from Japanese firm Omron Global that -- hey hey -- recognizes faces and their various features. Does the face have big eyes? Are they in trouble? What is the person looking at? The transliteration "okao" apparently means "face" in Japanese, according to their website. "OMRON is committed to raising the accuracy of face detection so that OKAO Vision can be used in many different lifestyle occasions and social settings," their website reads. iPhoto '09 must fit in with that plan. Omron has other facial recognition products, including software for mobile phones, and a camera-plus-hardware-plus-software console that can accurately tell if a person is smiling or not. The software works reasonably well, according to Gizmodo, but does pick up some false positives in patterns, or, say, Mount Rushmore.
Smile for the camera: iFace recognition for iPhone
If you have to be subjected to surveillance, identification and security profiling, might as well have a shiny iPhone in the mix to make the erosion of your privacy rights that much easier to stomach. That's the scenario now that Animetrics' iPhone facial recognition product, iFace, is in limited release (per the Manchester Union Leader). Paired with the company's FIMS facial characteristics database, the iPhone app will allow law enforcement or military personnel to do field analysis of facial snapshots and possibly identify persons of interest. While there are already portable devices that can be used to measure other biometric identifiers (iris imaging, fingerprints and the like), iFace is the first handheld product that will do facial feature recognition. Most of the testing for iFace has been done under controlled imaging conditions, so it's not clear yet how well the tool will perform in the real world.
NEC's ad system pumps out spots based on gender, age
For better or worse, targeted advertising isn't going anywhere. Seemingly, it's not getting any more discrete, either. NEC's Digital Signage Solution combines a camera, a large display and a FeliCa contactless IC card reader / writer in order to dole out advertisements that cater to certain demographics. The system includes the innate ability to determine "gender, generation and other attributes" of a person in order to serve up advertisements that will cause him / her to spend some dough. From there, the individual can scan their phone in order to access related content on their mobile internet browser. That's all and fine and dandy we suppose, but how on Earth do you convince busy citizens to stop by and have a look at an otherwise uninteresting flat-panel?[Image courtesy of NEC]
Expression recognition turns humans into remote controls... for robots
Jacob Whitehill at UC San Diego's Jacobs School of Engineering has demonstrated a proof of concept that allows his facial expressions to speed-up and slow-down video playback. Pretty sweet. But we're more interested to hear that his project is part of a larger effort at the UCSD Machine Perception Lab (gulp) to use automated face recognition to "make robots more effective teachers." We can see the future now...Human: (frowning) Robot: Aw, my meat bag is sad, I will now give it a hamburger and turn on Golden Girls. Fortunately, human teachers who've somehow missed out on the billions of years of biologically evolution required to recognize the "oh face" can take advantage of this research as well. See a video demonstration of that after the break, face-controlled video here.
Scientists devise software that can interpret attractiveness
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]
NEC rolls out LaVie laptops with "face pass"
It looks like NEC is keeping all its bases covered today, backing up those water-cooled desktops with a range of new laptops boasting some less-than-common specs of their own. Likely to attract the most attention in that regard is the laptops' "face pass" feature, which makes use of the integrated 2.0 megapixel camera to ensure that only you (or someone that looks an awfully lot like you) can access the laptop. Otherwise, the laptops boast a range of fairly standard specs, including your choice of Core 2 Duo processors on the top-end LaVie C model or your choice of Core 2 Duo or Celeron processors on the LaVie L model. Both models also pack 15.4-inch displays, with a Blu-ray drive reserved for the very top-end laptop. Look for the whole lot to hit Japan later this month, with prices ranging from ¥150,000 to ¥310,000 (or about $1,300 to $2,675).
Speecys shows of SPC-101C face-recognizing robot
After letting its MI-RAI-RT (a.k.a SPC-101) robot wander around aimlessly for a while, Speecys has now finally decided to let the bot have a look at the world, adding a cyclops-style camera to its new SPC-101C model. That'll apparently not only let it recognize faces, but expressions as well (we presume that's what's going on in the picture above). Otherwise, the robot appears to be same singing, dancing, and e-mail-reading bot we've come to know and fear. Those willing to let the thing in their house will apparently be able to get one (in Japan) on September 1st for ¥336,000, or just under $3,000. Be sure to check out the read link below for some more pics and a few videos.
FujiFilm's FinePix F45fd: an F40fd in Argos clothing
Attention Argos shoppers, their "only available at Argos" exclusive on the FujiFilm FinePix F45fd is not all that exclusive. Spec for spec, the F45fd is none other than the F40fd rolled up special for the on-line UK and Republic of Ireland retailer. Your 200 Quid ($407) takes home an 8.3 megapixel CCD, 3x optical zoom, 2.5-inch LCD, 300 shot battery, ISO 2000 sensitivity, and storage on xD or SD cards. Not bad but no reason to get uppity with your mates about an "exclusive." [Via LetsGoDigital, thanks David]
Emotion recognition software knows you want ice cream
Dutch researchers Theo Gevers and Nicu Sebe, known mostly for their work deciphering the Mona Lisa's smile, have created a face recognition system which can gauge a person's level of happiness. The scientists, working with the multinational goods-manufacturer Unilever, created a face-tracking algorithm which maps video of a subject's face into 3D regions, and then uses those regions to determine their level of pleasure. The tests followed European women's reactions to eating five different foods: vanilla ice cream, chocolate, cereal bars, yogurt and apples. Unsurprisingly, the scientists discovered that women enjoyed eating ice cream and chocolate far more than an apple or yogurt -- the latter even evoking "sad" expressions from 28% of test subjects. Unilever hopes to put the technology to work in creating products such as reduced-fat ice creams which elicit the same response as their full-fat counterparts, while the researchers will be launching a consumer version of the software sometime in August, as well as a website to analyze up to 1,000 user-provided photos daily.
Fujifilm's IS Pro DSLR lends a hand in forensics
Fujifilm has been lending a helping hand in the realm of investigative photography for quite some time, and the firm's latest picks up where the S3 Pro UVIR and IS-1 left off. Featuring Fujifilm's Super CCD Pro and Real Photo Processor Pro technology to see light from the ultraviolet, visible, and infrared portions of the spectrum, this 12.3-megapixel gem also sports face detection, password protected lockouts, optional "rubber body armor," CF / Microdrive slots, RAW support, and a live image preview LCD to boot. Moreover, it's fully compatible with Nikon F mount lenses and iTTL flash systems, which should ease the burden of switching costs if you've already sunk way too much into Nikon accessories. No word just yet on how much coinage this will demand, but look for it to land in precincts (okay, store shelves too) next month.
KornTech's Rogun robot recognizes faces and intruders
While KornTech's Rogun won't go down as the first humanoid that sports both face recognition and intruder alerting functions, it does one-up many of the other prototypes by actually being available for purchase. The Korean startup has developed a kid-friendly one-meter-tall robot that "recognizes people through embedded cameras and high-end face-tracking software." Additionally, the bot can walk on its own and "perform various functions suitable for a security guard or nanny" such as pace the floors at night and give its master a cellphone warning if it recognizes any suspicious behavior. Rogun can even use its camera to show parents what mischief their kids are getting into at home by beaming video via its integrated WiFi chipset, and if watching the big screen is just too 2006, the youngsters can focus on the seven-inch LCD set within the device's chest. Of course, video telephony, internet browsing, and priceless companionship also come bundled in, and while the company hopes to sell these fellows for a mere $5,000 in time, snapping up your own Rogun at the moment will run you a whopping $100,000 or so considering the current BTO nature of production.[Via I4U]
