If there is one feature on Facebook which delivers “social utility” magic even to the most average of users, it’s Photos. In fact the feature is so popular that by Facebook’s own account 1 billion photos are uploaded every month—a staggering number that makes it the largest photo site on the Web. However, as with all good things, there are also drawbacks, and in this case discovery is high on the list. While Facebook makes it super easy to discover photos in which you were tagged, there is no chance that every one of those billion photos are tagged each month. And that leaves a big opportunity.
Let me put it another way: How many photos of you are there on Facebook that you’re completely unaware of? Israeli-based Face.com will help you find them with ‘Photo Finder,’ a Facebook app that uses facial recognition to help members locate untagged photos of themselves and their friends. We have 200 special access invites available to TechCrunch readers who will be granted first access to the app, as well as preference on the waiting list. Get your invite here.
Once installed, the app will begin scanning you and your friends’ photo albums, a process that requires a bit of time to complete, but the welcome screen will immediately display photos that were ‘Auto Tagged’. Users can either accept, decline or identify the correct individual themselves. The only users that have veto power to alter or decline a tag are the person who uploaded the photo and the person tagged.
Facial recognition technology is taking off. Competing technology can be found in both Apple’s iPhoto and Google’s Picasa, but those are limited to searching only your personal collection of photos (although iPhoto lets you upload them with the tags to Facebook). With Photo Finder, you are not limited to your own photo collection. Users can search manually for photos of friends or browse for recently tagged ones. Users can also track specific users by flagging them for the “Watch List”. Photo Finder will prompt hits via Facebook’s ‘Notification’ window.
The facial recognition technology was developed from scratch by the Face.com team over a year and half. It was designed from the ground up as a low-cost platform to meet two specific requirements: The first is recognition of “Faces in the Wild”. This applies to everyday photos that suffer from such issues as low resolution or bad lighting, or where faces are obscured with sunglasses, for example. The second requirement is to have the technology be scalable. In this respect Face.com claims to be able to perform facial recognition on all one billion photos currently uploaded into Facebook every single month using only a few machines.
Photo Finder scans the photos of users and all their friends, along with “other albums in your wider network where there’s a high likelihood of your (or friends’) appearances.” To understand the sheer volume of backend work required, consider the following statistics: The first 150 users in Face.com’s system required 20 million photos to be scanned, resulting in 30,000 identified faces. My personal installation of the app required it to scan 79,449 photos which resulted in 11,933 tags of myself and my friends. Photo Finder will then go back and re-scan the albums after its initial scan to identify newly added photos.
The social tagging feature within Facebook Photos gives Face.com a major boost because it can use those tags to train its system. It is important to note that Photo Finder does not add or alter Facebook’s own photo tags. Tagging that occurs through the app is stored in metadata accessible through the Photo Finder app alone. Also noteworthy is the fact that from a privacy perspective Photo Finder piggy-backs on the users’ Facebook settings and does not alter them in any way. Also, none of the photos are stored on Face.com’s servers. These only perform the heavy lifting required for the facial recognition and the storing of tags added through the app.
Even though this is an Alpha version of the app and there are occasional bugs, it works remarkably well. I was quite surprised that it was able to correctly identify individuals in side shots, backgrounds, or in extremely poorly lit photos. It all depends on the amount of photos available, but as a rule of thumb the Face.com team aims for 90% accuracy. It seems that they have some real technology on their hands as evidenced by their scoring first place in the “Labeled Faces in the Wild” experiment conducted by the University of Massachusetts’ Computer Vision Laboratory (Face.com are identified as ‘Hybrid descriptor-based’ in the linked paper).
It’s clear that Photo Finder was designed for mainstream viral appeal and I must admit that I found the app to be VERY addictive, spending at least ten minutes tagging people every time I played with the app over the course of the past two weeks. I have a hunch that once made publicly available the app is going to be incredibly popular on Facebook.
Wow, this is truly a great idea. I have no doubt in my mind that once it is made public everyone on facebook will be using this to find pictures that they are not tagged in.
I’m testing it now, doesn’t seem to be working unless I am doing it wrong. It just says there are no photos found of me, and it is 100% done scanning.
you need to wait until it scans your photos
Haha…Eric you posted photos of girls only ..BUt still it’s a good app.
http://www.smartbloggerz.com
Thanks for the invite for this cool app!
Yeah, it’s very cool.
You guys just forget that this means even more transparency, meaning less privacy:
Whenever somebody takes a pic of you in a “compromising” situation (e.g. completely wasted at some party, etc.) and posts it on FB, you might find yourself tagged within hours.
Which means, surveillance by peers becomes even bigger and more efficient.
Thanks !
Thanks for the invite. Let me see how many pic it finds of me
No doubt this is a desirable feature for photo sharing services. Google Picasa also launched their face recognition feature a few months back.
This feature will save the time fb users spend on tagging their friends.
Another step towards the goal of Intelligent search! Cool…
http://www.siteometrics.com
This will be a great tool for staffers that want to find *every* bad (or good) picture of you out there before they make their hiring decision.
We’ll add it to the list of our HR tools
Thanks you scum bucket
Tom, you’ve missed the the crucial emoticon. We do not have an HR department, let alone a list of tools for it. We hire the people that we feel good about working with.
Never the less, the issue over this otherwise certainly great technology has to be raised and ppl have to be made aware of what they are faced with (pun intended).
Perfect tool for M — o –s–s–a–d and C–I–A. I guess the article that pointed FB to C–I–A is true.
Yeah, that’s right. Geo-IP lookup, silent drones yeah, yeah, must be.
If the face.com guys really wanted that market they could certainly be successful there. Their technology really is best of breed. They don’t want to go there.
Great domain name, perfect fit.
Cheers
Sahar Sarid
Bido.com – Social Auction
agreed, the built in branding power of the english language is amazing.
helo nice meeting you guys.. in happy to meet you in this sight.. my yahoomail..perantelyndon@yahoo.com
Congrats to Gil and the other guys.
I must say i truly believe in you and your product!
Way 2 go!
Wow they just crowdsourced a solution for every gov’t agency that is remotely interested in or relies upon surveillance and there is really no way to effectively opt out since you cannot control the addition of the content or the tagging of the photos.
We are all living in public now, get used to it. But the app doesn’t let you scan all one billion photos, just a subset one or two degrees out from your immediate social network.
So the CIA or FBI would have to start friending lots of people to use it as an effective surveillance tool. (Or they could just get a subpeona).
Erick,
This app resides in a foreign country, so they are not subject to the same privacy laws. They can give away the entire database to M O S S A D, etc.
The same thing is through with 90% of our phone records in US as well as the wire tapping of our phones. It’s all done in I S R A E L
Where our laws don’t mean anything.
Do some research and it will scare your pants off!
*true not through…got ahead of myself, I guess–lol
Damn those jewish dogs again, james! Perhaps you will eat sheep testicles as your last earthly meal before blowing yourself to bits in a crowded jewish daycare?
Plus I think the CIA could get their own technology to do this, why would they use a Facebook app haha.
I was stating a fact. Had I left the wow out of it, it probably would have been more professional.
As to get use to it – is that an argument or a taunt to drink the cool-aide? Seriously, that diminishes legitimate concerns about how information is obtained and used. I am no privacy expert and not looking to have a drop down – there is no doubt I am outgunned – but it seems reasonable to wonder how this information could be used and how they plan to generate revenues.
The fact that “the app doesn’t let you scan all one billion photos, just a subset one or two degrees out from your immediate social network. “ is a very cool feature and a reasonable limitation. It will help find friends and to find yourself in photos. In fact I am sure it would help find photos one might want removed from the social graph.
But it is not really a relevant as I am talking about selling the data to third parties, in this case the government. Maybe I should have been clearer that I tried to figure out the revenue model and the one that stuck out for me was law enforcement, customs, airport security and the intelligence community.
While I am sure there are great corporate plays for this as well, going after government agencies that are trying to figure out how to identify people in crowds by licensing a massive library of “faceprints” is pretty killer business model. They have a need, they have budget etc. If these guys are not thinking about this or something like it as a way to monetize, I would be shocked.
So, I repeat they have just crowd sourced a solution to a big problem gov’t agencies involved in surveillance,pardon the pun, face. And no you cannot opt out as you cannot control what your friends do regardless of how facebook or any other social network suppresses information within the community.
Now, in fairness, I think the creators of face.com have defiantly created a very cool and useful utility for social networks that could be a tremendous amount of fun and enhance the experience for any network.
In fact, I think the data in the hands of the right gov’t agencies used in the right ways would benefit just about everyone. But used incorrectly, well . . .
No doubt, a great tool – as long as you can control the content. Soon it will be available on Google. And all pictures of you can be found. From anybody; your familiy, your friends, your date, the recruiter for your next job…
As I stated previously: the ‘anonymity’ of the internet might finally catch up with us.
http://danielpu...ngines-outlook/
wow… hope i am not on there lol
It sounds useful, but it also sounds like a potential Facebook TOS violation. Do you really think they want robots bulk-scanning 70,000 photos at a time?
I won’t be surprised if a few people get their accounts suspended over this one.
i always like these ai technology
Good luck getting a job now. Already today I’ve gotten 20 calls about integrating this into the hiring process. For certain jobs a picture is required with the application. There is already a policy for several of my clients that applicants names are googled for both web site and image content (One of my side jobs for hiring managers and HR depts… Be careful what you say on \. fyi we all check there.) Now with this tech you damn well better believe that businesses are going to be using it to do bulk scanning for ‘potentially objectional imagery’.
Lets assume that .0001% of images are of an inappropriate nature for the sake of argument. The software can then find that there are 12000 images of a subject. Based on pure weighting alone it is by far statistically safer to hire someone that is only exists in 200 images versus 12000.
Risk management will love this. Already I am seeing requirements for social network information for security purposes (Two clients REQUIRE the password for any and all social network profiles maintained by employees due to security concerns and are checked randomly).
You’ll be chipped, tracked, and monitored at every turn soon, like cattle. Automagic facial recognition on social networking is providing too much information that is far too easy to exploit. There are no laws that prevent images be taken in context. A school that digs up a picture of you holding a rifle, say during deer hunting, can easily use that as an excuse to pass on hiring you simply because you have violent images involving guns. Context is subjective to the viewer.
At least without automatic recognition you can’t search easily for images if they aren’t tagged by hand, but this just creeps me out…
Right now businesses use weighted scales to measure personal profiles ‘objectional’ content.
Search for obscenities (1 pt per instance).Ok so you Facebook contains 350, check.
Image count, .25 pts per image, 126, check.
Posts involving work, 10 pts each, 120, check.
Total: 596
Ok canididate B only has a score of 88. Who do you hire when they both have the same qualification?
I see more and more of these social networking cheat sheets. I’ve seen HR depts requiring access to social networking sites (manditory friends for monitoring purposes) more and more now (We are still talking less then 5% but in 3 years it’s up to about 3%… 1% a year is scary…) and an app like this just spells trouble.
I’m not paranoid, I make a living doing this crap on the side. I will scan Slashdot, Facebook, Myspace, you Diggs, Flickr, BBC comments, etc. We pillage google indexed PHPBB boards.
My reports are simple:
Number of Post at each site
Number of Images found in 3 catagories
G,PG, NSFW
Number of obscenities in all posts
Number of friends per social site
This is a great tool for tracking down people in images (group photos) that WILL be exploited.
Remember, the technology as it stands may be a facebook app but that doesn’t prevent them from selling me an app that will dig through google using the same tech.
Please feel free to help them perfect the technology so we can use it to screen you better.
Scan us enough, and at a certain point we all look guilty of something.
So then these hiring policies will (and to some extent already are) focused not on finding the best candidate, but on excluding the most visible. If we’re all visible, they’ll need to find a new metric.
Also, why work for a company that requires social network access? There is more to life than your next paycheck.
Pretty cool, the original Orli seems to be the hottest still. Is this the way it’s supposed to work? It finds people that are almost as good looking but not better? This is a tough one though because Orli would be pretty tough to beat hottness wise.
She’s a nice looking girl with a friendly face. I’m not sure “hot” applies, though. Just sayin’.
Congrats to face.com !
I know the team for a long time.
Amazing and talented team with amazing REAL technology – I’m sure will get very far.
this is the real thing and I have a feeling that they will become a leader in the space.
Zvika
PolarRose in Sweeden had this for years now… I wonder how are they doing these days…
I always wondered why Riya didn’t use their powerful facial recognition technology on facebook.
How come facebook doesn’t sell apps?
Ways to monetize facebook
http://intellig...ups-events.html
Right, these are the same guys who were behind Riya and Like.com? They must be involved in some way.
Great technology.
Despite the privacy rules at Facebook, this is still somewhat scary that uploaded photos can be tagged to identify you or your family.
It’s one thing to publically post one’s resume and websites. It seems like another step to identify people and family with photos.
Mike’s personal life has been invaded by the public. Does this make it worse?
Any invites left?
Looks impressive. Would love to try this out.
Very interesting.
This reminds me of the another Facebook application, Autotagger (http://apps.fac...k.com/autotagr/). However, rather than searching for tags globally, the application detects faces in the user’s albums to submit to Facebook.
How do I get an invite?
Sounds great.
I signed up.. Do I need to do anything for the invite? Thanks =)
It only works on women, guy-geeks need not apply.
Hi Orli,
Nice product! : ) We’re aiming for the same goal: photo tag integration across all platforms. iLovePhotos syncs with Address Book (Mac app), which in turn works together with the Mail app and the list of iPhone contacts. We’re working on a Flickr and Facebook exporter. Stay tuned.
http://www.yout...h?v=oLmyRlf1AaI
i have tried it. It does work well for tagging photos.
and so it begins, the end of life as we know it, constantly being surveillance’d and identified. Big brother is watching YOU! Seriously.
Why don’t these nerds use this software to identify missing persons in dimly lit photos? Or criminals, people with warrants. Then there would be an actual use for the Internet; not just fun and games.
Couldn’t you pick up someone a bit more attractive than this long nose?
Indeed, whats up with that? The chick is ugly are you trying to kill this great app?
i wonder how they run this app using only a few servers. if 1 million people used their app do you think they will need more than a few servers?
I I had installed the app in the morning, so its been about 12 hours, it wasn’t able to get much information.
Next, I clicked on the “Who’s This Tab” …. so it gave me a picture of a few friends and I tagged them from my list of friends. Next, I searched on a few of my friends names and helped tagged a few more, where a % value assigned was assigned to the tagged user. And In some cases it was asking me if it was tagged correctly.
Next I noticed that the list in “Who’s This Tab” grew. So, It’s giving me a feeling that the pictures are getting tagged by users instead of a facial recognition software ?
Would love to hear from the Dev’s regarding the technology ?
Thanks.
Hey Ashu, this is Gil, CEO of Face.com. With the launch of our alpha we’re running crunching through 10’s of millions of photos, and running a little slow. As scanning progresses you’ll see more auto-tags come up for your friends (tags suggested automatically by the system), while only those we cannot identify will appear in the ‘Who’s This’ section. Typically a who’s this finding will receive a very low accuracy score when accepted, while ‘good’ findings should exceed the 50% mark, and automatically appear in the friend’s profile page. Ashu – thanks for checking out Photo Finder Alpha! Anyone with questions is more than welcome to contact me directly at gil@face.com.
This type of technology has been used in airports around the world for some time now, those that are concerned about their privacy need to ask themselves if they felt violated so far, cause the big brother has been watching u and face recognintion technology has been around for some time now. To the people behind face.com, big kudos !!!
Ghost of Riya every where I say!
) No one is going to crack this magic called recognizing a face with 100% accuracy. It just not going to work.
Great tool, I hope to see a dating tool made from it like square head round head or an API. {seesmic_video:{”url_thumbnail”:{”value”:”http://t.seesmic.com/thumbnail/p73pAAdvZq_th1.jpg”}”title”:{”value”:”Great tool, I hope to see a dating tool made from it like square head round head or an API. ”}”videoUri”:{”value”:”http://www.seesmic.com/video/qbMUpQsJdD”}}}
pls. you can always reachout to me through my line 08035240272
What about Flickr integration?
So what about a user who has their profile to block photos tagged of themselves to everyone. Will that user’s photos be revealed to friends who do a face.com search of that user?
Hi Rob, Gil from the face.com team here. All privacy settings in facebook automatically apply in Photo Finder as well. So if a user blocked his tagged photos, Photo Finder will not present any tags for that person. This is the same with private photos or albums. If you have any other thoughts or questions, drop me a line at gil@face.com.
That is a nice product. I can´t wait to test it – automatic facial recognition can be used in a number of ways. I´m thinking about law enforcement right now, e.g. the search for cons online especially on social networks.
This one is really cool
clever
Had no Idea this program existed..going to try it…this is awesome.
http://www.cafe...s.com/beachtote
omggg i had this idea months ago and wanted to implement it for my BSc final year project!!
…too late i guess
