- Who created that image? TinEye adds the iStockphoto and Photoshelter collections.
We are happy to announce that TinEye our reverse image search engine has grown its index again adding over 32 million images including the entire iStockphoto and Photoshelter image collections. This is great news for photographers, image buyers and anyone interested in copyright compliance and attribution.
Today the TinEye index sits at just over 1.2 billion images – yes, that’s billion not million – 1,267,565,027 to be exact. As we grow we have been looking at how to answer just one question:
- who created that image?
Why is this important? Simple: Attribution. Creators want to establish authorship of their work and also know where their images are used. TinEye facilitates both.
As TinEye’s index grew, TinEye became the defacto image registry. Every day TinEye answers the “who created that image” question and connects images to their source. TinEye does this without keywords or metadata. Simply use an image to find an image. This is what we like to call the beginning of the attribution movement.
To start we are adding the world’s stock photography images to TinEye to connect all images available for licensing to their creator and distributor. And that’s just the beginning.
Every day TinEye helps image authors by:
- linking images to the original author – this is about attribution
- allowing image buyers to find the proper distributor of an image to purchase it
- showing how and where images are being used on the web
- protecting against image theft
Maybe you are a designer and you’d like to purchase an image for a project and you have a thumbnail or comp image but you’re not sure where it came from. Maybe you’re in love with a certain awesome image and would like to see the author’s other work. Maybe you want to see who else on the web is using an image… maybe you’re the image author. It does not matter: TinEye connects the dots for you.
At TinEye, we want to index every image in the world to help you find what you are looking for. iStockphoto and Photoshelter are a pretty awesome step towards that but it does not stop there. We will be adding a series of stock photography collections in the coming weeks so please stay tuned. If you are interested in having your image collection added to TinEye, get in touch.
Start using TinEye or join the 500,000 people who dowloaded our TinEye Firefox add-on to make image searching a single click.
- Hacking with computer vision
Looking for tennis courts on aerial photos: how it works and using computer vision. Fun!
- Wikimedia Commons & TinEye
Since the launch of TinEye, we have had a great response from the Wikimedia Commons image community. Wikimedia Commons is a repository of free-content files, including images, that are either in the public domain or released under free licenses. These images are used in many of the Wikimedia Foundation’s projects, including Wikipedia.
Anyone can contribute to Wikimedia Commons, and the project is driven by volunteers; while they are careful to respect image copyright, researching the license for each image that is submitted can be a challenge. To aid in this effort, members of Wikimedia Commons have created automated plugins and image checkers driven by the TinEye search engine, to help research photos and locate the source of images.For an interesting browse, check out Wikimedia Commons member Shizhao’s TinEye bot, which allows you to see all of the interesting images that have been uploaded to the Commons and been detected elsewhere on the web by TinEye.
.jpg "binoculars2_psf")
- Expanding our TinEye index
Young TinEye is experiencing a growth spurt as of late, and he doesn’t show any signs of stopping. He must be eating his Wheaties.
We have been working away on our crawling approaches and our efforts are finally bearing fruit. For the past several weeks the TinEye image index has grown by roughly 2-3 million images per week using a series of new crawling approaches. This is a good foundation that we are now going to scale to bring you more images and current content!
You may not have noticed this since our TinEye results page rounds our image index to the nearest hundredth of a billion images (i.e. the nearest 10 million). But we’ve changed it to round to the nearest 100 thousand images so now it is easy to watch that number grow!
The expansion of our image index also means you will be seeing increasingly current content in your search results from blogs and other online publications.
So check back often and keep searching! Stay tuned for further developments as well as the ability to submit your sitemaps directly to TinEye.
- TinEye earns a star
TinEye helps Sheila Smart recover 1000 euros and that makes us happy. Here is her image and its unlicensed usage on a book cover:
- TinEye on the trail of the British National Party
I now know that I am not the only one who is TinEye-ing every single image I come across on the internet. I have become a TinEye addict. I am soon going to need to start a TinEye Anonymous group: Hello my name is Leila and I am addicted to TinEye! I bet I would be in great company. But on to the British National Party. Did you know that:
The UK Telegraph reports that pamphlets distributed by the far right party to 29 million homes ahead of this month’s European and council polls featured testimonies from five “typical Britons” giving their reasons for voting BNP. Turns out the BNP supporters were istockphoto images!
Stephen Paulger broke the story on his blog and the UK Telegraph picked it up and so did The Sun. Fascinating.
Keeping it real with TinEye!
- Seeing more than double!
Derek has a great little article about TinEye and the future of image recognition driven search over at About the Image. Since the launch of TinEye I have been keeping an eye out for images that I constantly see being used in outreach and marketing campaigns and I have noticed quite a few Everywhere Girls. I am very tempted to start a TinEye tracker just for business women with glasses or a girl blowing a dandelion used in the world of advertising. I am sure it would make for a few entertaining blog posts!
Derek’s article reminds me of Emily Steel’s article in the Wall Street Journal: When Marketers See Double.
TinEye is gaming changing, not only because it is a reverse image search engine: ie you give it an image as a search input to start your image search, but because it is the first search engine to allow you to actually see how an image is being used. It drives home the notion of image accountability and integrity.
[to be continued]
- 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!
and TinEye’s detective work finds her traveling beyond Germany! Stand out from the crowds and use TinEye next time you are considering that stock photography license! Happy searching.
- 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:
Via BoingBoing: My unexpert analysis concludes that these photos of a 100-foot long river snake from Borneo are as phony as a politician’s smile.
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.
Now mousing over this image shows a different story. The alignment is near perfect. No question this is a better match. Ladies and gentlemen we have a winner. Unless of course there is an even better match out there!
Subscribe via RSS
