I mean, c’mon, it looks like just a teddy bear! And maybe a teddy bear face doesn’t constitute a human face to some of you in the audience, but I like to think that our world has grown beyond such prejudices. I like to believe that we live in a world in which any face can be considered a face.

The only way this iPhone spot could have been better is if it found the Virgin Mary in a burnt piece of bread. It’ll happen. Just give it time. [Flickr via Geekologie]

Face Detection
Apple says it uses facial detection to determine the existence of faces, and then facial recognition to separate one person from the other. The problem is, that first step is far from a catch-all:

• It suffers from the typical face-detection problem of an incomplete picture—it won’t pick up all faces turned to the side, revealing just one eye. But far worse than that, it has a very hard time picking up faces tilted to either side, even if they’re otherwise perfectly clear and symmetrical. In other words, if the year is 2029 and Apple’s deathbots are coming for you, cock your head to the side, and they’ll just truck on by.

• The other problem iPhoto’s face detection suffers from is overconfidence. Sure, it makes sense that it picks up the faces of Mount Rushmore (well, at least Lincoln’s) but it’ll invent eyes and a nose from any old rumpled curtain or wood grain when it wants to.

Face Recognition
Once you get past the detection, the recognition kicks on. Some people are already saying it’s crap, but it’s remarkable when it wants to be. How do I know it’s working? Because on many occasions I have seen it correctly identify faces in frames in the background of a shot. But recognition has some hang-ups of its own:

• Once you name a person and click on their face on the corkboard, iPhoto suggests lookalikes, which you approve or reject by clicking. The first round of suggestions are mainly nonsense—iPhoto needs a lot of data to work correctly. Confirm the identity of your subject 10 or 20 times then click Done so the system can recalibrate.

• In the first round or two, recognition errs on the side of inclusion: A bald guy with a beard and glasses won’t just bring up similarly described gents, but will attract everybody who is bald, everybody who wears glasses and everybody with a beard. In my experiences, the images with the closest resemblance appear first, but as you scroll down, there are more and more random guesses. When it comes to babies, good luck—in those early rounds, iPhoto thinks all babies look alike. Again, you approve the suggested photos that are of the same person, and reject the ones that are not.

• Once you’ve done a round or two greenlighting more accurate shots of the person, it’s important to reject ones that are not. If you leave them there, iPhoto will keep on suggesting them. I found that, if two people look kinda alike, it pays to identify them both, and go back and forth between them confirming more and more shots, so iPhoto learns faster who belongs where.

• Baldness, hair colour and facial hair are all strong indicators for iPhoto. If your friend has a goatee or some kind of fancy moustache, don’t ever let him shave it off. Likewise, if your mum switches hairstylists and starts getting a different dye job, she may as well don full hunter’s camouflage. For some reason, iPhoto had an easier time discerning the blondes than the brunettes.

• People wearing glasses cause iPhoto to suggest matches of other people wearing glasses, in some cases people who are otherwise comically different. But iPhoto seems to have a lot of trouble with glasses in general, and can’t always grasp the glasses-wearer well enough to confidently suggest more of that same person. Sunglasses are obviously a problem for recognition, but people wearing sunglasses are often suggested for anyone wearing glasses, as if it was all the same to iPhoto.

• There are two kinds of recognition dead-ends you can encounter, where iPhoto won’t suggest any more photos for a person, even though you know they’re out there, and where iPhoto suggests an endless supply of random faces as potential matches, clearly unable to narrow it down further. Both are infuriating, and require you to go out and identify photos manually in hopes of jogging its memory.

• Pets are not guaranteed to work with recognition. I’m not going to slander the good people of MacLife by calling BS, but seriously, I can’t get neither cat nor dog to be recognised in any way by iPhoto, and I don’t believe it’s possible. You can identify them yourself, of course, but the reason it doesn’t pull up suggested shots containing the same furry animal is that it’s not looking at furry animals.

The Faces system is technically a time saver even when the recognition is not up to snuff, because by batching the more-or-less appropriate pictures together, you can tag them a lot faster than you otherwise could. There are plenty of user interface problems that I will address in the actual review, but in the meantime, I will leave you with this: After heavy testing for half a day, iPhoto became shockingly good at identifying my face. I can only imagine that, given more calibration and identified content, it will be better and better. My biggest fear is how many photos aren’t clearing the first hurdle—face detection—and are therefore left completely out of the system. Who would have thought that the recognition would be easier to nail than the detection? Not me. [iPhoto '09]

To enroll in the face recognition software, the built-in webcam on the laptop scans the face for prime areas, such as the eyes or more conspicuous facial features. The special photo, which does not have to be of high quality, is processed so that the key areas are enhanced and the contrast levels are adjusted to the expectations of the software.

Dong Ngo of CNET recently underwent a Skype demonstration with a BKIS technician. The technican then captured a photo of Ngo’s face, and produced a special “unflattering” photo five minutes later using a special algorithm. Ngo was able to use the photo to log in to his Lenovo Y430. The technician later then demonstrated this procedure on similar Asus and Toshiba notebooks.

In lieu of fingerprint scanning and the traditional username/password combination, face recognition software may not be the most secure way to protect data. Until then, I’ll just use my own “specially” produced photos (courtesy of Photoshop) to tweak that, uh, zit, maybe even change my eye color–ooh instant nose surgery–to log me in. But only after I post that photo of “myself” on my Facebook profile. Hah! [CNET Crave]

Video you’re watching is optimised for size depending on your distance from the wall. And when you walk away, it follows so that you never miss a commercial (Stay-With-Me-TV). IP cameras allow for life-sized videophone conferencing and remote learning. One of the niftiest functions is virtual photo manipulation, like in the cliched movie with Tom Cruise, allowing selection, rotation, zooming and discarding of images by arm motions alone (Easy-Gesture-TV). Panasonic allowed members of the public to try this out at CEATEC. The interface is basically intuitive but takes a fair bit of practice to master (the demo guy also admitted to aching arm muscles, and he’s got another five to ten years to go before commercialisation).

The tech uses range imagery sensors and what’s called Time of Flight light tracking for real-time 3D image processing. Finally, LifeWall can act as wallpaper or decor, giving the room a new look whenever fancy strikes. Exposed brick, anyone? – Tim Hornyak

If you have photos on a Picasa web album already, you can enable the feature in settings. It then scans all your photos in the Picasa web album, before grouping similar faces together. You then work through those by giving name tags.

You’ll quite often have to repeat the same person in different groups of photos, so it’s a far from perfect solution. But it does make the tagging process much quicker than manually going through every photo.

It’s also secure, enabling better searching and more freedom for specific collections of photos, and you can share tagged photos with the people in them easily as well. Any images you share via Picasa also only shares the nicknamed tag you’ve put on the photo, not any further details like contact information.

This is a really useful development for cataloguing your photos, but why it’s only available online and not in desktop photo management software like iPhoto or Picasa for Windows is beyond me. Hopefully we’ll see it rolled out to desktop applications sooner rather than later.

[Picasa nametags]

This is a good thing, because Sagawa Advance’s scanner is used as access to high-security areas such as power plants and medical factories where they’ve got to make sure that it’s really the plant supervisor entering and not his evil twin bent on the destruction of the human race. That’s always the worst. [Digital World Tokyo]

Plans are also afoot to include biometric testing on the spectators when the games start, in the Summer of 2012—an estimated nine million people. The Chairman of the Olympic Delivery Authority, John Armitt, claims that the system will be as easy as travelling on public transport (London-based readers will know, to quote esteemed philosophers Duran Duran, it’s about as easy as a nuclear war.) “The gates will be like the Jubilee Line,” he has been quoted as saying. “Put your hand down and it will open.”

The biometric system is not the only hi-tech addition to the games’ security. The policeman in charge of the games has gone on record as saying that London will need an additional half a million CCTV cameras to be put in place before the site opens for business. Yet again, the small matter of civil liberties is being brought into question.

While the head of Britain’s main construction union, Ucatt, claims that he is fan-goo with the security system, “providing the ODA guarantee that the biometric data will not be passed on to any third parties and will be wiped once the project is complete,” the ODA has not guaranteed that it will not pass on any information to government agencies.

How much of a logistical and planning nightmare this will be remains to be seen but, given the UK’s success when it comes to building big things—the Millennium Dome, and Wembley for example—there is a strong possibility that we will be seeing the Olympic flame being lit at an opening ceremony some time in 2019. [Times Online]

The software can be used on digital cameras, mobile phones and things of that nature to —well, I’m not sure. It’d be a useful little gadget to put in a screening room for a comedy, or measure how happy your friends are in your company. Either way, I eagerly await to see what creepy uses are thought of for this technology. [Akihabara News]