- 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).
- Preview: the spanking new TinEye APIs
I am sure you have noticed that we have been quiet on the TinEye front for a few months now. That’s because we have been busy building our TinEye APIs and also “dog fooding” our APIs. Oh I see you are not familiar with one of our favourite expressions? Eating your own dog food? Well, we have been eating our own dog food. By that we mean using our own APIs to build internal applications which of course led us to find that they needed much improvements prior to release! But improve we did, and we are ready to preview them at last!
But let’s start with a little addition for TinEye – the tiny reverse image search with a tiny 2 billion (but growing!) image index.
Drag and drop: now you can drag and drop an image onto the search page to start a TinEye search. Handy!
And now on to what we are very excited to introduce: TinEye Services.
These are a series of APIs that allow you to add image recognition to your application, enterprise or operations. In addition to the TinEye Commercial API which we previously launched, you can now license and start working with 3 additional APIs:
MatchEngine: Finds duplicate, modified, and even derivative images in your own image collection. You can think of this API as a TinEye on steroids, but working with your own images. It deals with even more extreme image modifications then TinEye. MatchEngine is fast, extremely accurate, and easy to integrate. It of course uses image recognition and image recognition only for its image search and comparison.
MobileEngine: Build mobile application that use high-sensitivity image recognition. This is the API to integrate in any application where you want users to be able to search by taking a picture with their mobile phone camera. Why use QR codes when you can use image recognition? MobileEngine has been optimized for mobile images and is extremely fast, accurate, and a snap to integrate.
MulticolorEngine: Search through your image collection using colors. You are probably familiar with this API as it powers our multicolor search lab. Now, you can have MulticolorEngine index your image collection so that you can search it by color. Want an image that contains blue, yellow and green? MulticolorEngine can do that. This API is not limited to just a single search color, it allows you to select multiple colors as well as the weight of each color in your search. And it does not stop at that: MulticolorEngine can extract colors from an image, or set of images, and it supports full metadata searching too.
- We love hackathons! Let’s go to HackTO! Join us.
We love hackathons at the TinEye HQ and this Saturday we will be participating in HackTO. HackTO is organized by HackDays. And HackDays = hack events across Canada. This weekend HackDays lands in Toronto with 10 API and a 100 attendees! Did you know that Toronto is the 4th best city in the world to get your startup off the ground? It is!
Why such love for hackathons? Because we can see that our entire tech and startup community benefits when awesome developers (and people) get together to hack, build and tinker. If you have not joined us at any of our hackathons, it is time to remedy that.
The idea behind HackTO is simple: a single day hackathon where developers build an application using a set of provided APIs and any other API they would like to use. Completed applications get a chance to compete for awesome prizes.
This time around, there are 10 APIs to select from including our MobileEngine and MulticolorEngine. You may already know the MulticolorEngine as Piximilar. We are launching a set of TinEye APIs in the coming weeks and of course rebranding all current APIs. So stay tuned for our next announcements and get a preview at HackTO. In the meantime:
This is the API that allows you to integrate multicolor searching for your own image database or extract colors from images in your database.
MulticolorEngine searches an image collection using one or more colors. We will be providing a two APIs for the MulticolorEngine:
- A read-only API pre-populated and loaded with 3 million Creative Commons images. You will not be able to add or delete images from this collection.
- A blank r/w API that you can load up with any images you like.
To get a feel for the capabilities of the MulticolorEngine, visit the Idée lab.
MulticolorEngine is a REST API with responses delivered in JSON or XML format. The main methods are:
- color_search: Used to perform a color searches against the collection and return any matches with scores. You can specify up to 5 colours with weights in RGB or hex format.
- extract_colors: Given an image, extract up to 10 colours and their dominance.
- extract_collection_colors: extract information about what colours exist within your whole collection, or a subset of it
- add: Used to populate your image collection.
- delete: Delete images from your collection.
MulticolorEngine also supports full meta-data searching but we’re recommending you not to get into this unless you really want to – it is still in beta!
MobileEngine uses mobile variants of the same algorithms that power TinEye. MobileEngine is designed to find a match for mobile phone picture in a collection of original/target images. It can find duplicate and altered versions of images using fingerprint based searching algorithms. It can find images that have been cropped, resized, rotated, flipped, obscured, blurred etc. Some examples of use are to match a book cover to a collection of covers. Same with CDs & DVDs, stamps, currency etc. It works with rigid flat objects but not 3D soft objects like clothing, fruit, or family pets!
The MobileEngine API can be integrated with any mobile application. For HackTO this API image collections is not pre-populated which means that if you want to develop and launch a mobile image search application integrated with this API, you will need to create a database of images for your search. The TinEye team and their documentation can assist you with that prior to the start of HackTO. Get in touch.
MobileEngine is a REST API with responses delivered in JSON or XML format. Each operation is completely atomic, meaning that given a request, other requests will wait for the first request to complete before they are processed. All responses from the API will have these keys:
- status: indicates the status of the request, can be one of ok, warn, fail
- method: the method that was called
- result: list of results for the method
- error: list of errors from the API
The main methods for MobileEngine are:
- add: Used to populate your collection. There is one shared collection for everyone to use, so please use a prefix for your image names if you want to make sure that they will not be overwritten.
- search: Used to search against your collection and returns matches. Optional search parameters are min score, max number of matches and horizontal flip.
- delete: Delete images from your collection by passing a filename.
Full documentation for the APIs will be provided at the start of HackTO just to keep things interesting :)
The full HackTO schedule is now online. And if the awesome TinEye APIs are not enough of a reason to get you to HackTO, how about the prizes:
- First prize: $2,000 (cash)
- Second prize: $1,500
- Third prize: $500