As quick and painless as this seems, Apple wants to simplify things even further for owners of its iPhones, iPads and other iOS devices. Imagine walking up to your phone or tablet in its dock and seeing the screen light up with a greeting. You pick it up and pull it a few inches closer to your face, and voilà! the screen is unlocked and the digital universe is instantly at your finger tips.

This is a feature already available on jailbroken iPhones, but one that works very slowly and can easily be hacked using a photograph.

Update: As some of our diligent commenters have pointed out, facial recognition unlock feature is also available in Ice Cream Sandwich, the latest version of Android. That implementation, however, has been shown to be easily fooled and Google has acknowledged that its not as secure as a traditional passcode.

The technology required to get this type of feature to work effectively is pretty sophisticated and, as Patently Apple describes it, "computationally expensive." The trade-off for using an alternative method is weaker security, which defeats the purpose.

In a somewhat jargon-loaded post, the Apple patent-watching blog describes how the company plans to overcome the challenges associated with implementing such technology. Their method would use a two-dimensional analysis of the placement of facial features as well as skin tone and check those details against "target images" previously captured by the device. This patent comes about a month after news of Apple's acquisition of a patent for advanced 3D object recognition, which could be used in a similar fashion.

Exactly how they would thwart creative attempts to hack the system wasn't detailed, but presumably they would have that sorted before this feature sees the light of day.

Plans like this point to the future of our interaction with computers and data. Motion-based gestural control is already here thanks to Microsoft's Kinect and the iPhone 4S has brought the most capable voice-controlled artificial intelligence application yet to the mass market. Siri is rumored to be coming to other iOS devices, including the iPad 3 and Apple's much-rumored HD television set, due to launch next year. Thanks to the curious tinkering of developers, we've begun to see what tools like the Kinect and Siri are capable of, and their potential goes way beyond desktop computers and mobile devices.

Facial recognition technology has been around for decades, but until recently it's been slow, inefficient and largely limited to proprietary implementations, such as databases used by law enforcement. That could all be about to change, and the results are bound to send shivers down the spines of digital privacy advocates.

"With Carnegie Mellon's cloud-centric new mobile app, the process of matching a casual snapshot with a person's online identity takes less than a minute," writes Jared Keller in The Atlantic. "Tools like PittPatt and other cloud-based facial recognition services rely on finding publicly available pictures of you online, whether it's a profile image for social networks like Facebook and Google Plus or from something more official from a company website or a college athletic portrait."

As incredible as some of the potential uses this technology has may be, the futuristic possibilities are largely overshadowed by the privacy implications raised by the widespread availability of point-and-shoot facial recognition. For every auto-tagged friend and identified criminal, there is inevitably a pervert and a ruthless despot bent on punishing protestors.

Google is well aware of the risks. Even before acquiring PittPatt, it had developed its own powerful facial recognition internally, but has declined to bake it into any publicly-released applications like Google Goggles because of these privacy concerns. Google Chairman Eric Schmidt has said that the privacy implications raised by facial recognition are "very concerning" and that the company would not likely lead any effort to popularize it in consumer mobile apps. Even so, third party developers haven't been deterred from working the controversial technology into Android apps.

Apple and Facebook Join the Facial Recognition Game (Carefully)

On Facebook, some users were disturbed when they first saw the social network's own implementation of facial recognition. Upon uploading an image of friends, Facebook will automatically identify people in the photograph and ask users if they'd like to tag them accordingly. The feature, which was made available globally this summer, allows users to opt out via their privacy settings.

Apple made clear that it intends to let the iPhone recognizes faces one way or another when it acquired a company called Polar Rose in 2010. While it has declined to integrate the technology into iOS directly, Apple has made facial recognition features available to developers in new APIs for iOS 5. On example of how this might be used is RecognizeMe, an app for jailbroken iPhones that unlocks the device by scanning and recognizing the owner's face.

Just because titans like Google and Apple have declined to roll mobile facial recognition out in a way that would allow the technology to be easily abused, that doesn't mean somebody else won't. As long as the tech exists and continues to improve, it may only be a matter of time before it's available on a smartphone near you.

What do you think about mobile facial recognition? Creepy or cutting edge? Let us know your thoughts in the comments.

According to Bloomberg, Jepsen said that Facebook will begin running online ads today that link users to their privacy settings, allowing them to opt out of the service. Have you seen the ads to which Jepsen refers? Have you or will you opt out of the "tag suggestion" feature?

Facebook users upload more than 100 million photos to the platform on a daily basis. A company called Divvyshot and founder Sam Odio were acquired by Facebook to help institute the facial recognition feature. Odio, the product manager for photos, left Facebook in June to create a new company called Freshplum.

Bloomberg also reported that Jepsen responded to problems with impostor accounts, making it easier to report and delete them. Facebook added "new language and links to a contact form to help users trying to report an impostor or fake profile." Part of Google Plus's trouble around using real names and not allowing brands on the platform at first had to do with authentication and dealing with potential impostor accounts.

Facial detection software is not just limited to the Web though. A new startup in Chicago called SceneTap uses facial detection and people-counting cameras to scope out your local bar to tell you "what is going on." What is the male-to-female ratio at your favorite club? Who is buying drinks? SceneTap cameras see it all and provide the data to users and bar owners. Seem a little creepy? Maybe not as much as you might think.

According to founder and CEO Cole Harper, the footage collected by SceneTap is not meant to be looked at by anyone. There is a demarcation between "facial detection" and "facial recognition" that SceneTap says it does not cross. The way it works is that there is a camera facing the door of the bar. A person comes in and the camera creates a box around the face, analyzing the eyes, nose and facial structure. It takes that data and scans it through a database to find the most similar type of match. Are you a 25-year-old female? That is what the SceneTap camera is trying to find out.

The cameras are not monitored by people and information is not stored. Bar owners do not have access to the feeds as the stream is encrypted from the backend. SceneTap does technically have access to the visual feed but Harper says that it would only be used for maintenance.

Big Data for Bar Owners for the First Time

The value proposition for bar goers and bar owners is significant. Fundamentally, SceneTap is trying to bring big data on a granular level to the restaurant industry. It analyzes what type of people are coming in, what they are buying and when they come and go. That information can be cross-referenced with promotions, advertisements and on-site staff (does Bartender A bring in more male patrons than Bartender B, for instance).

This is not the type of information that restaurants and bars have ever had access to. Even with the most sophisticated point-of-sale systems, the ability to have specific gender-related data on a timeline that can be studied over a period of time is not available. Yet, add SceneTap data with the POS system and all of a sudden restaurant owners know everything about their clientele.

For bar goers, it provides real-time information to help you decide where you are going. Is Bartender A working? How many girls are there and how old are they?

SceneTap will launch in Chicago in the middle of July and have partners in select cities across the country shortly thereafter including New York, Boston, Miami, Austin, Columbus, Phoenix, St. Louis, San Diego and Las Vegas.

Facebook does not tag people in photos automatically, but prompts users to tag friends that the facial recognition system recognizes. The service is opt-out in Facebook's security settings as opposed to opt-in. That aspect of the facial recognition feature and Facebook's approach to privacy altogether is what bothers privacy and security advocates like Sophos.

Cluley wrote an open letter to Facebook in April this year, calling for the company to go to a "privacy by default" doctrine as opposed to a privacy via opt-out policy, which Facebook currently employs for much of its information.

Cluley also does not think that most people are mentally equipped to handle the long and sometimes confusing Facebook privacy settings.

"Most Facebook users still don't know how to set their privacy options safely, finding the whole system confusing," Cluley wrote. "It's even harder though to keep control when Facebook changes the settings without your knowledge."

When Facebook unveiled facial recognition last year, it was uploading 100 million pictures to the site a day, with a good portion of those included people (who are likely also Facebook users). Companies like Viewdle and ActiveSymbols are bringing facial recognition applications to smartphones. Divvyshot and founder Sam Odio were acquired by Facebook to help institute its facial recognition program.

For its part, Google chairman and former CEO, Eric Schmidt has said that Google will never get in to the facial recognition game. That has not stopped developers from building facial recognition into Android, such as the application Recognizr.

If you are concerned about facial recognition from Facebook, you can go into your privacy settings and change them. Click "Privacy settings" --> "Customize settings" --> "Things others share" --> "Suggest photos of me to friends" --> "Edit settings" and disable.

CNN reports that Google is working on a mobile app that will use facial recognition technology to turn mobile phone photos into a means to identify people. The app would serve as a form of visual "search," displaying results including name and email address.

Updated: Google says it is not working on a mobile app of this nature and would not introduce any facial recognition technology into any of its apps "unless there was a strong privacy model in place."

While privacy advocates will be quick to identify all the dangers and implications of such a thing, Google is making it clear ahead of time that the service will be "opt in." Users will have to agree to let their faces and data be retrievable by the app.

No doubt, adding facial recognition technology to the way you're "Google-able" would be seen as a major privacy change.

But the technology to do this already largely exists, says Neven, whose company Neven Vision was acquired by Google in 2006. Indeed, Facebook has been working on facial recognition technology too so that photos uploaded to the site can be automatically tagged with users' names. However, while the technology at Facebook just uses data within, well, Facebook, the Google app would likely crawl the Web, including sites like Flickr and Picasa in order to link photos to someone's identity.

It's a similar process to Google Goggles, its image-recognition search engine for objects.

Google won't say what the production timeline is for the app or when it plans to release the product, (Edited to add: actually Google says there're no plans for the app at all) but it's clear that the company is already thinking about its strategy around the privacy - and the publicity - implications when this happens.

There's very little gray area on this one: You're either completely excited by the potential for built-in facial recognition combined with smartphones and social networks, or your entirely creeped out and afraid for the future of the planet.

The future is nearly here and I, for one, welcome our new overlords, who today come to us in the form of a Silicon Valley company called Viewdle that we first wrote about last October. Read on to find out how they plan to make what you see above a reality.

Last October, Viewdle raised $10 million and told us that it's primary function would be to assist with tagging photos on smartphones before they're even uploaded to sites like Facebook, that way they wouldn't get lost in the cloud. Today, however, Austin-based PSFK Salon writes that the company was out and about at the Mobile World Congress showing off a much deeper integration, wherein its visual analysis technology is used to link faces with social media.

Viewdle sits between the camera and the user analysing faces in the camera stream, identifying them, then offering links to Facebook, YouTube, LinkedIn, and other social media platforms. A user can identify and tag people in pictures & videos then pass the information to their social networks. As they tag others the software learns to recognize them, and can even share these new visual profiles with other users. The live view also offers an augmented reality tagging overlay that reveals information about the people around you.

According to Viewdle's website, a number of implementations are on the way, from ViewdleFaces to ViewdlePlaces to ViewdleGames. For now, however, Viewdle Uploader - a desktop program - is the only thing available. Its mobile apps, which it says are coming soon, stand apart from other recognition programs with one big distinction. They do all of the facial recognition procession locally, on the device, instead of outsourcing that functionality to the cloud.

What do you say? Are you stoked or completely creeped out? I know that I could use a little help once in a while and certainly wouldn't mind if a smartphone app could help me out. Maybe we're friends on Twitter already, but I'm blanking on a name or a context. Would it be so bad if I pointed my phone across the room and figured it out?

Fine. For now, I'll suffer in peace, wander over and admit that, once again, I have forgotten your name.

We spoke with Jason Mitura, the chief product officer for Viewdle, and he told us that the company would offer a real change in facial recognition technology by taking the process out of the cloud and into the device itself.

"If you put it on the smartphone, it doesn't need to communicate with the cloud," said Mitura. "We're making the analysis and recognition real-time. Our use-case makes it real time such that as you're taking the picture, it's tagged."

According to Mitura, the problem right now is that many users take numerous pictures and then upload them later, often without tagging the content. The movement toward real-time facial recognition in both photos and video will change how content is organized on the Web.

Kuk Yi, a managing partner with Best Buy, said that the company invested with Viewdle because of its movement toward real-time recognition and tagging.

"For consumers, it's all about real-time. Viewdle is leading the market by creating compelling consumer experiences that are both real-time and cross-platform," said Kuk Yi.

While tagged content can drive both pageviews and advertising dollars for publishers, Mitura noted that untagged content was "lost on the social graph."

"As our technology gains adoption," said Mitura, "I think you're going to see it spearheading the change from batch-mode uploading to real-time sharing."

Although Mitura wouldn't confirm any solid dates for product releases, we were told that we would begin seeing something from Viewdle by early next year.

We do have to agree that taking the tedium out of tagging all of your photos would be a welcome change. And having this functionality on-device, rather than in the cloud, could make for some interesting applications involving organizing and searching your media.

Unfortunately, this and all other end user-focused services are being terminated as the company switches its focus to its series of facial recognition products. Says Polar Rose's Thijs Stalenhoef, the service was "fun while it lasted."

According to Stalenhoef, the response to the facial recognition products introduced during the Mobile World Congress last February has been "phenomenal." These include the company's flagship FaceCloud server platform, mobile face recognition library FaceLib and FaceCore, a core face detection and recognition module for deep integration and other use-cases.

Unfortunately, the company has not been able to focus on the service at polarrose.com due to the popularity of these back-end applications and products. The Polar Rose service hasn't seen a new release in ages and support requests on GetSatisfaction have basically been ignored. "The site, as it stands today, is not up to the standard we set for it when we launched," admits Stalenhoef.

But instead of bringing on new staff to help better manage the consumer service, the company has decided to shut it down entirely. The company will close the service on PolarRose.com on Sept. 6, 2010 at which point all user accounts and corresponding data, including images downloaded from Facebook and Flickr, will be deleted. The tags sent to Flickr and Facebook, however, will remain in place.

Competition for End Users Ramped Up Over the Years

It's a shame to see such a compelling and interesting service disappear, but Polar Rose has had stiff competition in the consumer space as of late. Google introduced facial recognition functionality into its Picasa photo-sharing service, a Flickr competitor. Windows Live Essentials introduced facial recognition into its latest release. Also, Face.com, a facial recognition technology company, introduced multiple Facebook apps in 2009, including Photo Finder, a facial scanning service for tagging unidentified photos of Facebook friends, and later Photo Tagger, an app which automates the tagging process. And Facebook, as CEO Mark Zuckerberg recently revealed, hosts five to six times more photos than all competing photo-sharing services combined.

Meanwhile, Polar Rose may be finding its niche as the technology behind the next great facial recognition service or application. For example, last summer it partnered with Swedish software and design company The Astonishing Tribe to create an augmented reality concept application called Augmented ID, which employed Polar Rose's facial recognition technology in an app that recognized people through a mobile phone's camera in real time. Earlier this year, the app was re-branded as Recognizr and the company announced plans to ship the app as an Android application in a matter of months. That deadline, sadly, has since come and gone.

As for Polar Rose, it's no longer alone in the licensing game, either, when it comes to facial recognition technology. Rival Face.com launched APIs (tools that allow developers to incorporate the technology into their own applications) back in May of this year. These APIs, free during the early alpha stage of testing, have already been used to power marketing campaigns by Orbit gum and Axe deodorant. Future plans could involve charges - no word yet on that. In any event, despite losing the end user service at PolarRose.com, having multiple companies vying for dominance in the facial recognition space will ultimately be a win for consumers - at least those who aren't creeped out about the technology in the first place.

Improvements to the App

Since our last look at Augmented ID, it's clear that the company has been making great strides in the development of this mobile application. Most notably, the interface's design has been greatly improved. It now has a much cleaner layout and looks to be far easier to use. The social networking icons, for example, now appear big and bubbly, casually overlaid on top of each other in a row at the bottom of the screen, ready for dragging upward when you go to create your own profile. The same icons, all evenly sized, also float around people's heads after the app recognizes them. You can then tap the icons to see the profile information they contain. For example, a Twitter icon could showcase the user's latest tweets when tapped.

The recognition process, too, seems improved. A square shown by a broken line appears on your mobile's screen around the face you're trying to recognize. This closely resembles the autofocus systems found on most digital cameras today. When the app "sees" the face, the square's outline turns from grey to green and the social networking icons zoom in from all sides to float around that person's face.

The only downside to Recognizr (besides the fact that the prototype isn't available for use today!) is that it requires both participants to use the mobile application in order to work. That makes the app far less creepy than some all-knowing "Minority Report"-like technology, but severely limits its potential at the same time. Since the prototype is currently Android-only, too, the database of users available for facial matching would only include those who have installed the application on their Android phone and have taken the time to set up their own profile.

That's not to say that some future version of the application couldn't scour the web for faces to match - implementing this feature would be challenging, but not entirely impossible. There are plenty of photos on social networks to pull from in the case that a particular person wasn't already a Recognizr user. However, whether or not the company plans to develop their app to that point is unknown at this time.

Coming Soon to Android

After demonstrating Recognizr at the recent Mobile World Congress, Dan Gärdenfors, head of user experience research at TAT, announced that his company plans to partner with someone who can help bring the mobile concept app to market. He anticipates having a commercial application available in a little as a month or two.

You can watch video demos of both Augmented ID and Recognizr on YouTube, here and here.

Agents are not permitted to friend suspected tax evaders using false information; however, public information is perfectly acceptable. In the past, collections agents were aggressive enough to appear at residences, places of work and schools. If you thought old school debt collectors were tough, think of today's social media wielding bunch as the Terminator 2 version.

While they're unlikely to kill your next-of-kin after questioning them, they can garnish your family's wages and slowly lure you out of hiding. If the group has just caught on to Facebook and MySpace, imagine the power they'll wield once they start using facial recognition software and people search engines like Spock and Pipl. You've been warned. Pay your taxes on time and avoid an audit.

Earlier this year, a company called Face.com brought facial recognition technology to Facebook by way of an application called Photo Finder which scanned through untagged photos and identified the people within them. Now, using the same facial recognition algorithms that made Photo Finder possible, the company is introducing Photo Tagger, an app which scans through select online albums to automate the tagging process.

About Photo Tagger

But where Photo Finder focuses on discovery, Photo Tagger focuses on productivity. With the new app, you can choose the albums to scan - whether your own or those belonging to your friends - and the app will process the photos they contain. Photo Tagger will batch the people it finds into groups and will then suggest tags for them. Once you confirm the tags, they're automatically pushed to Facebook where the people tagged are notified, just as if the process had been done manually.

Facebook users who upload a lot of photos will find an application like this extremely useful as it dramatically cuts down on the time it takes to tag images. Instead of having to go through each photo one-by-one, you can simply confirm the tags the application suggests. And surprisingly, it doesn't make a lot of mistakes. The facial recognition technology employed by both of these applications is incredibly accurate. In our tests, the most common mistake it made was to identify a picture of a friend's child as the friend themselves - a problem that has a lot to do with how facial features between related family members are so alike. But for the most part, the app identified photos correctly.

The Photo Finder app has already produced amazing results. It has scanned more than 1.5 billion photos so far and has identified more than 2.3 million faces. What's even more shocking about these numbers is that the app is still in closed alpha. Imagine how many faces it will scan when it opens up!

Get in on the Alpha

Photo Tagger will also launch in closed alpha but will probably be closed for a shorter period of time than the Photo Finder application. The reason for this is because Photo Tagger scans albums on the fly as opposed to scanning an entire network of inter-connected users and their photos like Finder does - a number which can be on average over a hundred thousand photos. Since that causes a bigger impact on the service's back-end than Photo Tagger, it will remain closed for longer while the company works out the kinks.

No matter, because out of the two applications, Facebook users will likely find Photo Tagger the more useful of the two since it offers a more direct purpose: tag these photos fast!

Photo Tagger launches today in private alpha. If you want in, you can click this link to add the app to Facebook right away. Only the first 100 ReadWriteWeb visitors who do so will be given access. Good luck!

]]> Discuss]]>

AugmentedID uses facial recognition and tracking technology from a company called Polar Rose, a photo tagging startup. A few months ago, Polar Rose made the news when they released a tool that lets you tag your friends on flickr and then alert them that they were tagged via Facebook Connect integration. Although hyped as "facial recognition for flickr," the technology isn't a part of the photo-sharing site at all (although if Flickr was smart, they'd soon find a way to make that happen). Instead, Polar Rose, at its very core, is simply a facial recognition algorithm which pulls in photos from flickr to its site for tagging. It can also be integrated into any web site you own via a javascript widget. Apparently, it can now be integrated into mobile devices, too.

Polar Rose performs facial recognition by matching 3D models of faces, one of the three methodologies for performing this task. This technique captures the shape of the face and other distinctive features like the contour of the eyes, the nose, and the chin. The advantage of using this technique is that it's not affected by low lighting scenarios - a useful feature when used in real-world mobile interfaces like that of Augmented ID.

Current Limitations and Future Possibilities

Unfortunately, in order for Augmented ID to know a person's face to begin with, it appears you first have to set up an Augmented ID account. Once that's done, you can maintain different profiles for your public persona versus your private one, switching between them as desired. Each profile has associated with it your contact information, web links, and information about your social networking profiles. Another Augmented ID user could then aim their phone at you and Augmented ID would recognize who you were and show them the appropriate profile - which is actually the video stream of you in real life with the various links sort of hovering around your head.

This isn't exactly the ideal mobile facial recognition solution just yet since it requires both participants to use Augmented ID in order for it to work. But it is one step closer than anything else we've seen before. In a perfect world, however, anyone could use the app to identify anyone else - regardless of whether or not that person had created an Augmented ID profile.

Of course, implementing that type of feature would be difficult, but not impossible. Given the numerous public photos on the web, an app could, in theory, use its facial recognition technology to compare the 3D model of the face in the live video feed to those out there on the web as opposed to ones in its own database. A good place to start this matching process would be Facebook. Despite the millions upon millions of photos on that social networking site, facial recognition already exists there courtesy of the new app Photo Finder. Perhaps the two companies could even work together so the mobile app could query against the photos Photo Finder has already turned into 3D models for matching purposes. (Is that technically possible? If that's your area of expertise, let us know).

That's getting a little ahead of what Augmented ID actually does, but possibilities like this are exciting.

But For Now...

At the moment, Augmented ID is more of a mobile "concept" than it is a working application ready for download. Still, it's only a matter of time before technology like this is adopted and put into use in the real world. In fact, that's why TAT developed it in the first place. The Swedish company designs and builds products and services that "enhance the user experience of portable devices." They work with OEMs including SonyEricsson, Motorola, S60, Samsung, Vodafone, and Orange as well as partners like Texas Instruments, Freescale, Teleca, Macnica Networks, Montavista, Nvidia, and Symbian. In other words, you may one day see this technology come built into your mobile device. But we'd settle for the Augmented ID mobile app -wouldn't you?

Face.com's facial recognition software is able to scan through millions of photos in a relatively short amount of time. Although the results of the scan are not immediate upon adding the application, you're able to view them even while the scan is in progress. There's no exact time frame for how long this process takes - it depends on the number of friends and photos you have available among many other factors. However, Photo Finder does save its results for future use - if your friends later add the app too, it won't need to rescan the photos that have already been analyzed.

To begin using Photo Finder, you simply add it to your profile as you would with any other Facebook app. You then click the "Get Started" button and Photo Finder will launch its scan. There's nothing else you need to do until the scan is complete. You can leave the page to return to other parts of Facebook or even close the web page altogether - Photo Finder will continue to run as you've already granted it offline access when you initially added it.

After Photo Finder has finished its work, you can return to review the results. You can click on the "Me" button to see your own photos or click on the "Friends" button to discover those belonging to your friends. Next to each user, all the Facebook photos of that particular person are displayed. The ones in which they're already tagged via Facebook are outlined in blue and the ones where they've been "auto-tagged" by the application are outlined in orange.

On the auto-tagged photos, you can click a green checkmark to confirm the match or a red "X" if the match is incorrect. Upon hitting the red "X," you're presented with a dialog box where you can fill in the name of the person who is actually in the photo or you can click a button that reads "unknown" if you don't know who it is.

If you'd like, you can later navigate to the "Who's This?" section within the application to help tag all the "unknowns" in your network. The software also identifies how accurate a match is by displaying a percentage beneath each photograph.

To keep track of the photos of your closest friends, Photo Finder presents an option that allows you to add people to a "Watch List." This is a section of the application where all the related photos for those on the list are tracked.

Privacy Concerns?

The Photo Finder application may sound a bit frightening at first, given its capabilities to uncover long-lost and hidden Facebook photos. However, the company has taken great strides to make sure that its application respects your privacy. For one, the app will not tag photos within Facebook itself - they are only tagged within the application, meaning no one can see them unless they too are running the app.

Photo Finder also correlates its settings with your Facebook privacy settings. So, for example, if you've specified that a certain subset of your friends may not see your tagged Facebook photos, that is also reflected within the application.

When you're auto-tagged in a photo, you are the first one to be alerted via Facebook's notification mechanism. You can then either approve the photo or untag it (hide it from the other users of the Photo Finder app). If you untag yourself, none of your friends will be alerted to this action.

The Technology

The algorithm behind Photo Finder has been in development since 2007. Unlike many of the facial recognition algorithms out there today, this one does not require people to face the camera head-on in order for it to be accurate. Instead, it focuses on identifying people in "everyday photos" - that is, photos taken from different angles, out-of-focus shots, photos in low lighting, or those in which people are making odd facial expressions, etc.

That the algorithm excels at matching people with their pictures has been at least partially confirmed by an independent study conducted by the University of Massachusetts. Here, the Photo Finder team contributed but one aspect of their algorithm for examination and its accuracy far exceeded that of its competitors. You can see the results of that study here - the Photo Finder algorithm is identified as the "hybrid descriptor-based, funneled" model which is seen on the chart with the highest "true positive" rate.

Join the Private Alpha

The Face.com technology has been in private alpha testing for a number of months among a group of 150 users, mostly friends and colleagues of the founders Gil Hirsch (CEO), Yaniv Taigma (CTO), Eden Shochat, and Moti Shniberg. During that time, 20 million photos were scanned, identifying around 30,000 people.

You can join the private alpha by clicking this link here: http://face.com/invite.php?promo_code=S226566001

Only 100 members are invited.

The company is not able to confirm an exact date as to when the app goes public, only that they expect that sometime later this year, after tens of millions of photos have been scanned, they'll know better where they stand. They don't want to rush things - it's one thing to open up the app to select users, it's quite another to make Photo Finder available to scan the 15 billion photos hosted on Facebook. But one day in the not-too-distant future, that's exactly what they plan to do.

Face.com is currently angel funded and looking to raise a VC round.