- Open TinEye! And other stuff…
Well folks we’ve heard you loud and clear: “We don’t want to log in to use TinEye“. Good news! TinEye is now open for anyone and everyone to use, without the need to log in or register. Our registered friends – and there are almost 200,000 of you – however, will enjoy some great perks.
And there have been some other changes too!
- Registered users of TinEye will get the opportunity to try out new features first, and provide feedback. You will also be able to link to and share your search results with friends. You will also have the option to keep a search history, including a gallery of images with search dates and the number of results found. And don’t forget that registered users can subscribe to the TinEye newsletter to stay in the loop. Now would you just go and register?!
- We introduced automatic discard of search images after one hour. If you are unregistered–or if you are registered and have disabled search history in your profile–anything you upload to TinEye for search is discarded after an hour.
- We updated the TinEye plugin for FireFox to version 0.5. This update includes a bug fix where if text is highlighted with a background image beneath it, the plugin is not activated.
- The little business of ads appearing on TinEye. Well, they have arrived because little TinEye wants some fluids (especially Robot Oil and Bourbon). You want a free reverse image search engine right?
- We made improvements to search speed and you should be able to play with a faster and sharper TinEye.
Just for the new folks: TinEye is still only searching a 1 billion image index which means if you don’t find a match for your image search it is not the image recognition technology, it is the index! But now that we have this release out the door we will go back to working on the little things: like growing our index!
So what should you be searching for this morning? Well how about the Obama Hope image that is all the rage this morning? or the little angry baby? Happy searching folks and welcome to the future of image search brought to you by the good folks at Idée.
- 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.
- Multicolr Fun
Every once in a while we get an email from someone who has played with our lab technologies and built something fun and exciting. Last month I received an email from my good friend Patrick and since then it has been sitting in my inbox begging for attention! I am such a delinquent when it comes to emails! But that said: Patrick has an awesome career: he spends his time building exciting project, exploring how technology can enhance people’s lives and experiences. You may have seen some of his projects around Toronto. Just recently he built the TXTris wall version 2 which was showcased during HoHoTo on Monday. It was awesome, and I know a few of us spent time sending Tweets just to see them scroll down the screens (some the tweets were not fit to print so we won’t be repeating those here!).
Patrick was inspired by our Multicolr search to build a little prototype: this prototype basically takes a stream from a webcam and picks out the dominant colours and passes them through our Multicolr Search to find photographs that match those colours. Very, very neat and you can view it here:
- Stunning Multicolr search from the good folks at idée
Thank you. Thank you. Now back to work!
- Multicolr lab
Yesterday was October 23 and that was Smurf anniversary! And I missed it. I had all the intentions in the world of doing blue searches on the Multicolr lab but you know bizness got in the way! If you are not familiar with the Smurfs, hurry up and read up (thank you wikipedia). For me, growing up, the Smurfs were Les Schtroumpfs.
Their stories were bold adventures and they made Spirou my favourite magazine! Now in honour of Peyo and his Schtroumpfs, I gave you blue multicolr searches! If you want to try these yourself head over to the Multicolr lab and have fun. Happy belated Schroumpf day!
- TinEye: the ‘go to’ search engine for images
TinEye fan Jeff left us a quick note to let us know that he spied TinEye in action over on Digg. The post in question – Awesome Spaghetti Junction, what city is this? – included the image below and the simple question:
What city is this?
How can you find out more about an image such as this one when the image is all you have? Simple. Use TinEye.com. TinEye is the only search engine able to find your exact image in over a billion images crawled from the web.
Digg user ka9dgx used TinEye to find the image in a National Geographic Traveler story about Bangkok, Thailand. TinEye also located the original image titled “The Veins of Bangkok” on Flickr, just one of the 26 different instances of this image found on the web.
And who took this shot? Trey Ratcliff, a part-time photographer that I first learned about back in August when I wrote this post about Copyright and Creative Commons. You can see more of Trey’s amazing images by visiting his blog Stuck in Customs.
Click the image below to try the TinEye search yourself and discovery where else Trey’s image has travelled online. Still need to get your TinEye account? Grab one here.
Image: Trey Ratcliff
- To pose, perchance to sleeveface…
To // Sleeveface // : one or more persons obscuring or augmenting any part of their body or bodies with record sleeve(s) causing an illusion.
Here’s the official “How to Sleeveface” video:
As we told our friends at the iParty, the best of the sleeveface snapshots will win a prize. Jen Dodd clearly pulled off a winning sleeveface with her Nina Hagen look below, so she’s queued up for a prize for sure.
Who else do you think deserves a little something for their sleevefacing efforts? Leave us your comments with your top two picks from the photos below and we’ll tally up the votes and award two more prizes.
Okay, so those are our contestants for the prizes. But wait! I have a few more snaps for you – here are the idéalists avoiding work on a Friday afternoon by sleevefacing:
Happy sleevefacing friends! If you try it out remember to post a link to your photos in the comments, we’d love to see them.
- 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
- Search Flickr for Multicolrful Images
Idée’s Piximilar is the technology behind the Multicolr Search Lab. While most colour search tools can only identify the dominant colour in an image, our technology allows you to choose up to 10 colours from a palette of 120 different shades (thought it can handle any colour palette imaginable).
Cameron Parkins from creativecommons.org says our Multicolr Search “is a ton of fun and a great way to find some really beautiful CC-licensed images” and Website magazine calls it “a must for bloggers, or anyone else who wants to get photos with a specific color scheme.”
Here’s an example search by blogger Aditi
You can adjust your search results by adding more of certain colours and less of others to feature your favourite colours more prominently in the images returned. Abhijeet shared our colour search tool with the readers over at makeuseof.com and demonstrated how you can dynamically search with just a few clicks.
From a selection of orange-based images…
…to the ‘pop’ and interest of oranges, greens and browns.
As you pick and choose your colours the search results automatically refresh with images that represent your new colour selections. When you click on any image it directs you to that photo on Flickr so you can learn more.
Looking for images of buildings? Try a grey-blue search combo, pulling in the colours of stone and sky.
Bryan Lee who blogs on OriginalProgram.Intermissions has a really great example of Multicolr in action with his black and purple search, below. His thoughts? “Here’s a great resource for finding color coordinated photos through Flickr. Whether you are designing and need it for storyboards, or simply want to mess around on the web, this makes for a great little web app.”
Here’s another search idea. Using bright colours and plenty of white I created a “comic book and cartoon characters” inspired search:
The combinations are endless.