- German EverywhereGirl?
By now you are all (too) familiar with the EverywhereGirl… but the Praegnanz.de blog in Germany seems to have found the German Everywhere Girl. All these stock photography business images are becoming all too familiar!
- TinEye on BoingBoing
Well TinEye is a myth debunker! He is a fake photo buster. A couple of days ago the UK Telegraph reported that there was perhaps a giant snake lurking in the Borneo river but Mark Frauenfelder from BoingBoing smelled a doctored photograph:
Well yes, they are. Fromage who is a TinEye user pointed out that the photograph was a fake and that one of the original photograph could be found here. Here is a link to the entire TinEye result set.
- Will the real Obama Hope photograph stand up?
I am sure you are wondering what does image recognition have to do with Obama? Me too! A couple of days ago – this is super old news for the blogosphere! – James Danziger posted about how he spent months searching for the original photograph that Shepard Fairey used to create his Obama Hope image. I am sure you have all seen the Obama Hope work?
Reading James’ post (which I linked to a couple of days ago) I thought boy if only he had access to the image recognition we take for granted within the Ideeplex walls, his months of research could have been shortened to minutes (James, meet TinEye. TinEye meet James. Now be nice)! But I digress: upon hitting publish on my short post, I received a comment from Waldir who pointed me to a series of Flickr photograph where Stevesimula identifies another photograph as the original. Bam! Would the real Obama Hope photograph please please stand up? No really! Sometimes the most obvious things are the ones that escape you: well, champion how about using our image recognition technology and comparing all the contenders? I mean we can surely spot the fakers? That’s what we ended up doing yesterday but unfortunately I did not have time to post about it. So the results are in and the winner is: Mannie Garcia who shot Obama for the Associated Press.
Stevesimula was the first one to complete his own analysis and came to the above conclusion before we did, we basically took our sophisticated image recognition technology and confirmed his finding.
Tom over at Phillynews did an awesome detective job to locate the original Obama photograph. Read his sleuthing!
Here is what we did: we took the Obama Hope poster and matched it against the two potential source candidate images. For this we used the image comparison engine of TinEye‘s bigger, more powerful brother: PixID. If you thought TinEye can compare images, you should see what PixID can do! PixID takes a detailed look at the patterns of the pixels images, creating digital fingerprints of the source and target images. It can find a small partial match in the fingerprints, even if the images have been heavily transformed. Edits can include crops, flips, rotation, skews or as in this case – literal posterization of the image.
PixID can also calculate a sub-pixel accurate transformation matrix that shows how the images best align to each other. We used that to produce the images shown below. Basically Mannie Garcia’s photograph was the best match.
Below you can view the results. As you mouse over each poster, it will swap to the best possible alignment of the source image we compared it to. If you toggle the images back and forth, you can see the real winner is obvious.
This is the Reuters images which was initially identified by James as the correct match for the Obama Hope poster.
As you mouse over the image to the right, to toggle between the poster and the aligned photograph, you will see that the alignment seems a bit off. Clearly Obama’s head and ears do not line up well at all! So what’s going on? It turns out that the mathematically best alignment possible was to have the lips and nose line up properly (take a look and you will see that they do). If you force the head and ears to line up, then the nose and mouth will be way off. Either way this is not looking like a good match to us.
- They came, they saw, they installed TinEye Music…
Last night we hosted a little event here at the idéeplex to share the latest toy we are working on. We were lucky to have a great group of folks from the Toronto tech community join us to ‘kick the tires’ of our soon-to-be-released beta app for iPhone.
Thanks to everyone who came by and made the night a smashing success. It was really exciting for the team here at Idée to see TinEye Music, the first iPhone application of our visual search technology, out the door for beta testing.
With TinEye Music you use your iPhone to take a photo of any album cover. Almost instantly that snapshot gets compared to our index of over a million album covers and the app sends you right to the iTunes page for that artist where you can preview songs, buy tracks or even purchase the entire album right from your iPhone.
You can learn more about our app by watching our quick little video or reading today’s posts by Mathew Ingram and Adam Schwabe. Jevon from StartupNorth beat all of us all to the punch, however, with his TinEye Music review posted during the party.
On top of the great conversations and lots of music searching with our TinEye iPhone app, we also did a little “sleevefacing” last night. If you aren’t familiar with the term “sleeveface“, take a look at some of our guests demonstrating it here and here. Amber MacArthur channelled her inner J.Lo, Libin Pan did his best Steve Jobs pose and Jen Dodd rocked on as Nina Hagen (Jen, you win sleeveface of the night, we’ll send you your prize!). It was a lively night for all.
This photo Rannie took of Jevon performing “the TinEye maneuver” with his iPhone is one of my favourites, followed closely by Alice’s snapshot of the other Beta at the party last night.
Well, the fun might be over but the work is not. This is just the beginning of bringing visual search to the world of mobile technology and we have a lot more in store for you, stay tuned!
** Photo: Jevon strikes a pose – Rannie Turingan
- TinEye: Sleuth in Advertising
Camera shopping is hard work. Over the past ten years I’ve purchased three digital cameras, and each purchase was more difficult than the last. Thankfully sites like Digital Photography Review, and Steve’s Digicams have made it easier because the camera companies are not exactly objective.
One thing I learned today is that camera manufacturers don’t necessarily use images that come from their cameras. For example, this Sony DSC-T3 viewfinder implies that the image is being captured by the camera. In actual fact, it’s a photodisc stock photo that predates the camera by years, and was likely taken with a film camera costing thousands.
- Automatic face replacement? Check!
I had not seen this paper about automatic face replacement to deal with privacy issues for example.
[...] we present a complete system for automatic face replacement in images. Our system uses a large library of face images created automatically by downloading images from the internet, extracting faces using face detection software, and aligning each extracted face to a common coordinate system.
This is awesome: of course I am thinking about Google street view (or any other mapping system) being entirely populated with people whose faces would be derived from a database of say 50,000 available faces to deal with any privacy issue. That would be interesting. The 50,000 sample faces themselves could be generated from a series of faces! This paper makes for a great read.
- Image tracking
The evolution of Hollywood paparazzi from a marginal nuisance to one of the most powerful and lucrative forces driving the American news-gathering industry is a phenomenon that dates back to March 2002, when a women’s magazine editor named Bonnie Fuller took over a Wenner Media property called Us Weekly, which had drifted along since its founding in 1977 as a rival to the fantastically successful People magazine franchise. What Fuller brought to Us was a keen understanding of her audience. “Every day, we’d look at tons of pictures that came in and lay them all out on a conference table,” Fuller remembers. “And what was interesting to me was to look at celebrities going to the dry cleaners and pumping gas. I loved looking at these pictures of celebrities who were just like us.”
- Everything is Visual: Introducing the TinEye Mona Lisa Widget
Because we love to have fun at the idéeplex we came up with a snazzy, embeddable widget that demonstrates the image identification technology behind TinEye: the image search engine!
What is TinEye you ask? Given an image to search for, TinEye tells you where and how that image appears all over the web – even if it has been modified.
When you want to find out where an image is being used on the web, you submit it to TinEye by uploading it, pointing to it on the web or right clicking using the TinEye plugin.
The image itself is analyzed instantly, and its “fingerprint” is compared to the fingerprint of every single image in the TinEye search index of almost half a billion images.
The result? A detailed list showing all the images and the websites using that image, worldwide.
All of the Mona Lisa images in our widget were found on the web by searching on TinEye for the first, unedited Mona Lisa image in the series. We took the results of our search and put them into this image flow interface, which allows you to scan through all the images and see the differences between them.
Give it a try, press play! This little widget is embeddable: this means that you can simply grab the code and embed it on your blog or website. Go ahead, we’re cool with you sharing and distributing it. Do you like it? You can Digg it too!
Did you know that the Mona Lisa is one of the most used images in product marketing in the world? While we only used 150 unique Mona Lisa images in this nifty little demo, TinEye actually found almost two thousand results searched over 487 million images!
Try pulling one of the Monas out of line, she’s snap right back in. Go forward, go back, stop to look more closely at an image. Interested in one? Click the corresponding url and off you’ll go to one of the thousands of websites featuring Mona Lisa in all her variations.
What is this? You don’t have an account yet? Today is your lucky day! We have 500 ‘instant’ accounts to our beta available. Sign up!
- Cool Searches from our TinEye fans
We asked, you answered!
We asked you what TinEye search just knocked your socks off? Which one made you laugh out loud? What search made you look around and say “I just have to show someone this, it’s so cool!”?
And you answered us. We’ve had hundreds of submissions to the cool searches page! Thanks to all our fans for sharing and for having as much fun with TinEye as we do.
Now, on to the searches!
Because we love robots and science fiction at the idéeplex we couldn’t pass up Steve’s “Because it’s Star Wars, dude!” search. TinEye found 99 variations on his original search image including a framed wall art version and even a half obscured poster! Great search Steve!
Checking in at a rather mind-boggling 272 matches, everyone’s favourite mom-to-be Angelina Jolie. Thanks to several of our fans for this cool celeb search. TinEye found hundreds of matches in our still small (but growing!) index of just about half a billion images including crops, colour changes, blurs, and image overlays.
It would just be wrong for us to not include a coffee search, we’re java junkies here at idée! TinEye located over 500 Starbucks images from the original search query, the standard Starbucks logo. Whether the sign, the cup or even the logo with major alterations, colour changes or mostly hidden, TinEye found them all!
Sometimes there aren’t very many results but they sure are funny. We were pleased to see that our little squirrel cowboy found a little squirrel lady friend, thanks to TinEye!
Some other fun searches included the Linux mascot:
Super Mario (without his mustache even!):
And a few fun shots from the Matrix movies:
Thanks for all the Cool Search submissions, TinEye fans! Keep’em coming!
- Thank you TinEye Community!
It’s been a busy week here at Idée and an even busier one for TinEye! Since our TinEye beta launched, we’ve had users from all over the globe trying out our image search engine, providing feedback and sharing their results! And we have to say: we love you, we love your feedback and we are working super hard on the next release.
TinEye has gone around the world and made some incredible friends in the US, Canada, Japan, Hungary, China, Germany, Italy, France and the UK to just name a few countries! So we want to thank you all from the bottom of our (robot) heart!
We found out that we have an amazing group of TinEye fans in Hungary at the Stock.Xchng forum, lead by photographer Cris DeRaud. It is great for us to see TinEye helping photographers locate how and where their images are being used!
In their words: “This is something really mind blowing. We are probably witnessing the development of a technology which is going to be used at a regular basis by people like us.” Amen!
Popping over to the British Isles, we heard from David Hoffmann of the Editorial Photographers United Kingdom and Ireland, who said “This is very impressive…this is a real breakthrough.” We could not agree more!
Photographer Robert Kneschke, from Germany, used TinEye to find unlicensed copies of his images in his first searches with our little tiny image index. Don’t worry folks: the image index will be growing very soon!
On to Italy where a blogger at Giavasan described TinEye as “a new search engine for images that kicks ass” and said it is “literally a dream come true.” Wow, we feel the same way! We’re glad you liked the simple and intuitive interface, quick search results and the Firefox plug-in too! Grazie, siamo contenti vedere cosi tanto d’interesse nel prodotto!
Susan‘s highlighted some great uses for TinEye and we are greatful: “It has the potential to be hugely useful once coverage is more complete, especially to image producers and their agencies who want to keep tight control on where and how their images are used. Very useful for image purchasers too considering web usage of an image – they could check pretty easily who else is using it and for what purposes to make sure there aren’t any unforeseen and potentially embarrassing overlaps in the same market.”
We want to thank you all from the bottom of our hearts because without you all these long nights would not make sense. Stay tuned for more TinEye goodness to come your way. If you have not requested your TinEye invitation all we have for you is a single question: What – are – you – waiting – for?