- MulticolorEngine Lab: Get my color – or color extraction
MulticolorEngine, the API powering our color search lab is now available for licensing. You have probably already played with our color search lab and already experienced addictive color searching but if you haven’t give it a whirl today.
This API can be integrated with any image search collection to allow users to search by colors. Well suited for e-commerce and image centric website and requiring no technology infrastructure changes, this API’s features include: the ability to index images by color, search by color as well as extract colors from a single image or a series of images – amongst many other features.
Today we would like to feature MulticolorEngine’s color extraction feature. To showcase this feature, we created a lab that allows users to extract colors from their images in real time. Drop by the lab, play with the feature and let us know what you think; we would love your feedback (link to contact form).
Using this MulticolorEngine lab you can:
- upload an image
- drag and drop an image
- or provide a URL to view the colors contained in your image.
MulticolorEngine will display a color palette for all the colors identified in your image. Color extraction works for JPEGs, PNGs and GIFs. Colors are displayed in RGB or HEX values.
and since this week is shark week:
And make sure to click on the colors on the generated color palette for a surprise multicolor search!
Shark photograph (c) by IVES.one
- Color search to make you smile!
It has been a busy few months in the TinEye HQ!
Our TinEye APIs are finally out of the oven and ready to take for a spin – we will talk about these another time – as today I would like to tell you about one API: MulticolorEngine. This is one of our favorite APIs and once you have played with it, you will join our fans!
Of course we are biased but we believe that MulticolorEngine is very likely the best color search engine in the world :)
Some of you may remember that a while ago we released a color search lab. It was our playground to use our color search technologies and figure out all the kinks of a color search API before we introduce it to the world. We basically sat down and ate our own dog food to wrap up development of our color search API. This new color search lab is powered by our new MuticolorEngine API. And you will get a pretty good feel for what this API by visiting and playing with the new lab.
The color search lab searches a 10 million creative commons image collection from Flickr. Of course you could integrate the MulticolorEngine API with any image collection and search it by one or more colors.
Now let’s step you through searching by color in our lab.
Let’s start by picking a single color. Summer green! (we made the color name up by the way!):
But what if you felt like a little orange? in addition to the green?
And how about some yellow to enhance that summer green and orange?
See how our color distribution changed:
There are a few ways to alter the color combinations you have selected: by using the slider and just changing the percentage of color in each color selection or by simply adding more of a single color. If for example you had a green and orange combination and you wanted to see what would happen if you added more of the same orange: all you would have to do is add more orange and continue until the desired results start showing up.
Continue adding colors to your selection and MulticolorEngine will continue fetching the images that contain your color selection.
But suppose you no longer love your orange color selection?
Just click on the trash can and it is gone.
But now let’s say you don’t like the current shade of red you have selected. We have a solution for that as well – we know how attached people are to very specific colors! Click on the color wheel icon to bring up a full color wheel and select your desired color.
Change the red and get a new set of results:
As with any new release, there are still lots of enhancements and features we would like to add and we would appreciate your feedback.Got a few minutes, well, play! and let us know what you think before we get to polishing this release.
And oh, one last thing: we have heard that sometimes you have a color code and would like to search for exactly that color, without going through an interface. Well you can do that via the page’s URL:
Notice the above highlighted code? That’s a hex color code and you can alter it to whatever hex RGB code you like!
MulticolorEngine: hand crafted in Toronto (Canada) by the TinEye team and a lot of caffeine (and sometimes beer).
- Copyright Reform: yes, let’s go!
I am looking forward to seeing some of the copyright reform recommendations rolled out soon. If like me, you have tried to use the search functions to find copyright information for a photograph or any works, you know what I mean. You – like most of the Copyright Office users probably still have forehead bruises resulting from your head hitting a nearby concrete wall (or handy hard surface).
On all seriousness: it is about time to bring the Copyright Office forward. So if you are in Washington, join us for an afternoon conference: Toward a Copyright Office for the 21st Century, a Public Knowledge Conference discussing the future of the Copyright Office. This conference will build off of the ideas put forth in Public Knowledge’s recent whitepaper, “A Copyright Office for the 21st Century: Recommendations to the New Register of Copyrights”.
This is incredibly timely as the Librarian of Congress will be appointing the first new Register of Copyright since 1994. The new Register will be the first appointed in the Internet era, and will have an opportunity to shape the Copyright Office for the 21st Century.
I am excited to be joining the conversation and participating in a panel presentation this afternoon along side:
- Tracey Armstrong, President and CEO, Copyright Clearance Center
- James Cavanaugh, National Director and Treasurer, American Society of Media Photographers
- Jule Sigall, Associate General Counsel – Copyright, Microsoft
- Respondent: Maria Pallante, Acting Register of Copyrights
- Moderator: Michael Weinberg, Public Knowledge
With the advances made in image search and image recognition based search, perhaps the next Copyright Office Database is simply the web!
- 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.
- 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.
- Expanding our TinEye index
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!
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 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!
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]