Flickr Search Hack Powered by Mouse-Made Doodles

Carl Bialik from WSJ writes "Retrievr gives budding artists an impractical but addictive way to find photographs on Flickr: a search engine powered exclusively by mouse-made doodles. From the article: 'Retrievr, Mr. Langreiter says, "doesn't look at specific forms." Art history buffs might like to think of it as photo-search by way of Impressionism. The Retrievr engine dissects a photo like a gallery connoisseur who lost his bifocals: It focuses on regions of colors rather than specific shapes and lines. "It is, actually, a simple scheme," says Mr. Langreiter. Retrievr creates and stores a compact representation of each photo in its database. The system pulls only the most important features — broad shapes, blocks of color and spatial relationships between different colored areas — out of detailed images to create shorthand approximations of every photo. (The storage mechanism extracts the 120 "strongest" features from an image to create something called a "wavelet transform," which contains much less data than the photo itself and facilitates lightning-fast searches.)'"

Comments

Flickr Retrievr

[tonyr1988]

Direct Link

Requires Flash.

Re:Flickr Retrievr

[RuBLed]

It's powered by "mouse-made doodles" and apparently you're not doodling enough. :)

Re:Flickr Retrievr

[HUADPE]

FTA

In its current incarnation, Retrievr runs on a single computer.

Ow. The Slashdotting. It hurts.

That was quick

[Centurix]

I think we just made the world record for the most number of boobies sketched out on the internet simultaneously.

Re:That was quick

[kbob88]

either that or, knowing the audience, the most number of cool-looking dual AMD Opteron Linux boxes sketched out!

That was quick

[5of0]

Already partly slashdotted. Very slow and sometimes you don't get in.
But this is an interesting idea, fun if nothing else.
I drew a tree and I got a pineapple with a guy's face in it, a chinese guy standing in front of a gate, and a dragonfly. Maybe I need to brush up on my drawing skills.

*groan*

It's been done before

[pyite]

I read about this a little while ago. Same principle. It uses a Haar transform (for those unfamiliar with multimedia signal processing and wavelets, specifically, the Haar transform is a specific wavelet transform based on the Haar wavelet and the associated orthogonal basis). The idea is that you compare the low frequency component of an image to the low frequency component of a rough drawing (which is pretty low frequency to begin with) and they should be pretty close of the images have anything in common.

Re:It's been done before

[pyite]

Haar wavelet though? While it's easier computationally (since the mother/father wavelets are peicewise linear in the 1D case) I always saw it as being a "lesser" wavelet in the sense of compression/reconstruction quality and ability to discern edges/other dramatic changes in data

I'm just saying what imgSeek uses. It's certainly a very easy wavelet to implement via lifting. I think it's probably used because more complex wavelets wouldn't be of any help since the rough drawing is so rough to begin with. In the end you could probably do the same thing with a DCT. Wish I had time to experiment.

Applied to museums?

[andphi]

To find Van Goghs, draw a whirlpool.
To find Pollocks, draw a can of paint.
To find Warhols, draw four cans of paint.
To find modern art sculptures, throw the tablet against a wall.

Other flickr Mashups

[vijaykiran]

This is very old .. I read about this first on webmonkey in Feb.

Ten Best Flickr Mashups
by Michael Calore 24 Feb 2006

Here's the link: Ten Best Flickr Mashups

Rating the doodles

[inKubus]

Keep in mind that there's a rating system for the doodles also.. there's some pretty cool artwork in there, as well as 50% boobies, dicks and strange V shapes (everyone draws them a little different). Pretty fun, it's under the Art of Retrivr

Feature Vector

[ArikTheRed]

120 features get mapped into a feature vector, effectively pinpointing a position in 120 dimensional space. All of the other images are indexed in the space, and it's a simple nearest-neighbor search to find the best matches. The interesting thing here is that funky things happen to space when you are in very high dimensions, and without creative indexing, it may be just as quick to do a scan and compare against the whole database. Obviously, not optimal. That's what they mean by "simple", since some multimedia search systems deal with indexes of thousands of features - thousands of dimensions.

Urg

[hyfe]

(The storage mechanism extracts the 120 "strongest" features from an image to create something called a "wavelet transform," which contains much less data than the photo itself and facilitates lightning-fast searches.)'"

If you're going to simplify, atleast get it somewhere near correct. A wavelet transform doesn't extract features. Features is a human-made concept. A wavelet transform is simply a transform (or for this purpose, a very lossy compression algorithm), very similar to the Fourier Transform, except that it has locality which is why it performs soo much better on non-uniform data.

I mean, 'something called a wavelet transform'. A short explanation linking it Fourier might have been apt, but wavelets are hardly voodoo.

'facilitates lightning-fast searches'.. oohh, thanks for telling us. I would never have guessed that after transforming the data down to 12 vectors, searching would be a lot faster. I mean, if they actually had indexed the data in a clever way or something specifically to speed up searches, this sentence would have made sense.. but they just transformed it. It's not voodoo and market-speech is bad!