- The future of search is already here
The Agency for Science, Technology and Research (A*STAR) in Singapore is organizing the first-of-its kind global competition to foster the development of the world’s next-generation multimedia search technology. This is a great way to kick start and cross pollinate some of the research happening in the world of multimedia searching. But what I found fascinating is what the agency had to say about the future of multimedia search:
Next-generation multimedia search technologies will transform the way users interact with rich-media material, an emerging need with the exponential growth of multimedia content and the proliferation of user-generated platforms like YouTube, Facebook and Flickr. With such technologies, users will no longer need to rely on traditional text-based search engines, which require each multimedia material to be tagged in text - a process that is laborious, expensive and limited by how the creator have chosen to describe the content.
Could not agree more!
- 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.
[If you can’t see the widget click here]
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:
An eyeball:
George Bush (as a trekkie and a clown!):
Super Mario (without his mustache even!):
Fox Mulder’s beloved “I Want To Believe” poster from the X-Files:
And a few fun shots from the Matrix movies:
Thanks for all the Cool Search submissions, TinEye fans! Keep’em coming!
- Taking TinEye for a spin
Michael from macro art in nature takes TinEye for a spin and is impressed. His review and comments are pretty much in line with what we have been hearing these past weeks: TinEye is an awesome image-to-image search engine when it finds results! Well of course, of course! What would an image search engine be if it did not find results! As we mentioned our index is growing, our next larger index is about to be released (so hang on to your pants). This is just the beginning of our image search adventures.
What I liked about Michael’s comments are his butterfly findings - because yes…. drum roll… TinEye does find results. We keep seeing modifications and adaptations to images that are quite stunning and that shows “the amazing capability that [TinEye] has” in Michael’s words. All good news!
- TinEye gets an Internet Explorer plug-in!
While the folks around the Idéeplex might be big fans of Firefox, we know that there are a lot of you out there who are perfectly happy with Internet Explorer, thank you very much.And what have you been asking us for? An IE plug-in to allow you to search using TinEye with a right-click option, just like the one TinEye already has for Firefox… we’ve been listening and now your IE plug-in is here!
TinEye allows you to search the web for images in one of three ways:
1. Upload an image from your computer
2. Point to an image that is already on the web (via a url)
3. Install the TinEye browser plugin for Firefox or IE, so you can right-click on any web image to search it
TinEye instantly analyzes your query image to create a compact little digital signature or ‘fingerprint’ for it and then searches for your image on the web by comparing its fingerprint to the fingerprint of every single other image in the TinEye search index. Cool!We hope that all our fans out there that are IE users enjoy the new TinEye plug-in. Now you can merrily right-click all the images you want to TinEye!
Enough talking? Off you go then, download the plug-in (you’ll have to sign into TinEye first).
You don’t have a beta account yet? Learn more or request an invite.
As always, if you have any comments, questions or even more suggestions send’em on over to tineyefeedback[at]ideeinc.com.
Happy Searching!
- TinEye Podcast
I had a great time talking with Jim Goldstein about TinEye and his podcast is now available for your listening. Jim Goldstein is a stunning independent photographer who has photographed some of my favourite locations in the world including Point Reyes. I am in California next week and I will be running here. If you have any questions about the podcast: I am listening at lboujnane (@) ideeinc.com as always. Oh and while you are downloading podcasts, Jim’s interview with Lessig is a must.
Thanks Jim!
- 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!
Gareth and the great folks at bit-tech took some time to check out TinEye and we were thrilled to know that one of the UK’s leading tech review sites really dig us. Thanks guys!
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!
Nearer to home - that’s Canada for all you visitors! - the forums at iStockPhoto have been buzzing with news about TinEye. All good.
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.”
More TinEye ’sightings’ from around the web? TinEye was discussed during a Canadian podcast and profiled in the National Post too!
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?
- Spot the iPhone!
Over a year ago Jason Kottke photoshopped a Windows desktop onto an iPhone and posted it on his very popular blog. Yesterday it was spotted on an Australian TV news show. Today, I used TinEye to see if indeed this wonderful photoshopped iPhone (I mean who would not want an iPhone running Windows XP) could be spotted anywhere else. And you guessed it: this little image is famous!The iPhone running Windows XP is even on eBay for sale!
- Big Index! Getting Bigger…
Indices…That’s what dreams are made of! Our TinEye search index is approaching 500,000,000 images; that’s half a billion folks!
Killer Kitten on TinEye. View full size.Half a billion may sound like a lot, doesn’t it? Well it is really just the beginning and that’s a tiny portion of all the images online today.
We are officially launching TinEye, our image identification based search engine, in a closed beta. What does this mean? You can request an invitation and servers permitting we will provide one! And you will get to play and experiment with the world’s first image identification search engine.
TinEye has been garnering great reviews already, from “the next frontier for web search” from the National Post to “indistiguishable from magic” from Jeff Barr, Amazon Evangelist to “image-recognition company that is second to none” Mathew Ingram.
You are all familiar with the Google or text based approach to searching: insert keywords in the search field and retrieve search results. TinEye uses an image as input instead. Rather than entering text, you upload an image to TinEye or you give it an image URL. It’s that simple! TinEye then uses our search index to retrieve where your search image has appeared in all the websites that we have indexed. No small feat.
And for your viewing eyes the TinEye video:
- Project Codename TinEye Launched in Private Beta
We not-so-quietly launched our internet-wide image search engine codenamed TinEye to our private beta testers today.
TinEye does for images what Google does for text.
Just as you are familiar with entering text in Google to find web pages that contain that text, using TinEye, you enter an image to find pages where that particular image (and modified versions of it) appears.
It’s a big step for us because our algorithms are now thousands of times more efficient than they were just a few years back. Uploading an image, and looking for matches in an index of over 487,000,000 images in real time is now a possibility. It’s something we’ve dreamed of doing for a long time, and now our beta testers are all over it.
Here are some of our favourite search results. The top image is the query image, and beneath it is the results.
Search Image
Results
Search Image
Results
Search Image
Results
Subscribe via RSS
