Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×

Flickr Search Hack Powered by Mouse-Made Doodles 79

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.)'"
This discussion has been archived. No new comments can be posted.

Flickr Search Hack Powered by Mouse-Made Doodles

Comments Filter:
  • Flickr Retrievr (Score:5, Informative)

    by tonyr1988 ( 962108 ) on Tuesday October 17, 2006 @11:45PM (#16480575)
    Direct Link [systemone.at]

    Requires Flash.
  • by Centurix ( 249778 ) <centurix@gNETBSDmail.com minus bsd> on Tuesday October 17, 2006 @11:54PM (#16480633) Homepage
    I think we just made the world record for the most number of boobies sketched out on the internet simultaneously.
    • Re: (Score:1, Interesting)

      by Anonymous Coward
      I wish you could take a peek at what other people are "searching" for with this tool at the same time; it would no doubt be profoundly entertaining and troubling.
    • Re: (Score:3, Funny)

      by kbob88 ( 951258 )
      either that or, knowing the audience, the most number of cool-looking dual AMD Opteron Linux boxes sketched out!
      • If the only images it has are of pornography and hardware... Kind of like trying to greb a Chinese text file for words in German or English, then returning 10 'closest' matches.
    • by StressGuy ( 472374 )
      This can be a problem. For example, I won't be able to check out the actual demo until I get home because I don't know what image it may pull to my work desktop.

      For those of us that run xscreensaver, one of the hacks goes out and gets random images from the web. I had to turn that one off because, random or not, it was getting porn everytime it ran. Now, I'm not a prude, I'm not concerned if my 5 year old son sees the image of a naked woman on my computer screen. To have a problem with that is to have a
      • This leads in to why I support the idea of .xxx domains. If you want access to it, fine with me. All I ask is that you make it easy for me to discriminate what my kids are exposed to. I want them to be able to use the internet and me to not have to worry about what they might find.

        That theory only works if you legally require that all porn be on .xxx domains. Otherwise you're still going to need to worry. Given that free speech protection has been extended to porn, demanding a subset of free speech to s

        • I think you are confusing categorization with restriction.

          As for it not being a perfect solution....conceeded...but it would help enough to be worth it. Finally, it is my understanding that most porn sites want the .xxx domain because it makes it easier to filter. Many of these site have links to NetNanny, et. al. on thier cover page.

          What remains are a whole slew of other site that still require adult supervision....but what doesn't.

          I support the .xxx domain because it makes it easier to filter harmful co
    • by HTH NE1 ( 675604 )
      If you sketch a stick figure, do you get emaciated supermodels?
  • FFS! (Score:1, Funny)

    by Anonymous Coward
    20 minutes of expert artistry
    are there no nipples on flickr?
  • Hmmm... Think about the combination of this and online dating sites! Especially if I could upload a target photo instead of sketching! ... I think I have some old Cindy Crawford JPGs laying around here somewhere (*dream on*).
  • That was quick (Score:5, Interesting)

    by 5of0 ( 935391 ) on Wednesday October 18, 2006 @12:03AM (#16480695) Homepage
    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*
  • by pyite ( 140350 ) on Wednesday October 18, 2006 @12:12AM (#16480749)
    I read about this [imgseek.net] 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: (Score:1, Interesting)

      by Anonymous Coward
      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. Seems like you'd have better luck with one of the Daubechies wavelets. I imagine though this really would depend on the source images, resolutions color depths, etc.

      Or maybe they could use the Mexican Hat wavelet. That one is
      • by pyite ( 140350 ) on Wednesday October 18, 2006 @12:32AM (#16480869)
        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.

    • by sholden ( 12227 )
      That's just what I thought when I read the article summary - "so? I was using a program that did that with my image collection years ago - though I recall it being a pain to get running in the first place".

      And I saw at least two demos fo similar systems (it's what prompted me to give imgseek a try) for searching image collections (one was draw what you want to find, the other was more pick from displayed images to extract features to search for). That was at least 2 years ago - since I left that country tha
      • Re: (Score:3, Insightful)

        by pyite ( 140350 )
        Hooking up with an online collection of photos might be new I guess - but that seems an obvious thing to do.

        Yea, I hate to preempt any of the people who have come up with things like this, but I hope no one tries to patent any of these ideas. It's sort of a process that's implicitly defined by the existence multiresolution image decomposition. We shall see.

        • Yea, I hate to preempt any of the people who have come up with things like this, but I hope no one tries to patent any of these ideas. It's sort of a process that's implicitly defined by the existence multiresolution image decomposition.

          Yeah, well, the purchasing process implicitly defined by the existence of an item for sale, a website entry of that item and a mouse button, didn't stop a certain company to patent a certain process utilising a certain number of mouse click(s).

  • Sounds like a pretty high risk factor for Hanta virus infection :P
  • by andphi ( 899406 ) <phillipsam.gmail@com> on Wednesday October 18, 2006 @12:51AM (#16480979) Journal
    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.
    • by iworm ( 132527 )
      I tried it and it returned a load of old Pollocks.
    • This is great for finding paintings, but what about songs? Can anyone tell me what song this is? It goes like Duh daa daa dum dum, dahhh dahh daaaaah. Thanks!
  • Oops I made the search xplode
  • Other flickr Mashups (Score:4, Interesting)

    by vijaykiran ( 789275 ) on Wednesday October 18, 2006 @01:09AM (#16481073) Homepage
    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 [webmonkey.com]
  • Rating the doodles (Score:4, Informative)

    by inKubus ( 199753 ) on Wednesday October 18, 2006 @01:27AM (#16481167) Homepage Journal
    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
  • ...how does this help me find pr0n?
  • For a second there I read "Mouse-Made Doodies"...

    Finally, a good use for surplus mouse poop!
  • Feature Vector (Score:3, Interesting)

    by ArikTheRed ( 865776 ) on Wednesday October 18, 2006 @02:17AM (#16481419) Homepage
    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.
  • Some kind of first-pass search system to find rough matches between Flickr/Youtube/etc posts and copyrighted material will be a big win for the MPAA. There are ways to align and compare pictures, but they're computationally expensive and compare two images, they don't do a general search. This thing might be usable as a first search used to find possible matches, which then get a more detailed examination by the expensive algorithm.

  • I tried to draw boobs and got this instead http://www.flickr.com/photos/19406332@N00/41144732 [flickr.com]

    I think it needs some bugs worked out. It searches as well as a search engine.
    • You just failed to notice that her cheeks look surprisingly breast-like, especially when you compare the 7th orthonormal basis vector of the wavelet transform of her face to the transform of your poorly-drawn boobs.
  • Interesting technique. I used things called Active Shape Models [man.ac.uk] in my MSc thesis which do pretty much the same kind of thing if I understand the article correctly. I've since lost touch with the academic research. Can anyone who still works in the area give me a quick run down of the differences and pros/cons?

    Bob
  • whatever I draw, this picture at http://www.flickr.com/photos/96302514@N00/58916441 / [flickr.com] is always in the list of results!
  • wavelet first (Score:3, Informative)

    by mennucc1 ( 568756 ) <d9slash@mennucc1.debian.net> on Wednesday October 18, 2006 @04:05AM (#16481901) Homepage Journal
    just for the record: the post claims that ``the storage mechanism extracts the 120 "strongest" features from an image to create something called a "wavelet transform"'' but this is quite misworded. Indeed if you look into the original research project, [washington.edu] you see that ``the algorithm performs a wavelet transform [wikipedia.org] on every image, and then collects just the few largest coefficients from this transform''.
  • But don't take my word for it; see for yourself! http://i11.tinypic.com/48bt477.png [tinypic.com]
  • Urg (Score:4, Informative)

    by hyfe ( 641811 ) on Wednesday October 18, 2006 @05:38AM (#16482331)
    (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!

  • I wonder, is Google looking at these alternative search methods? He mentions in the article that to do this to the entire Flicker would take 'some sort of Google-like infrastructure'...
    I used to assume that, being the current king of text search, Google would be expanding into more intelligent media searches, like this kind of 'similar image'-search, automatic tagging (like automatically indexing a picture 'nature' and 'winter'), and searching for songs by entering a couple of notes.
    They never did though, a
  • Is it just me, or does this thing always find nothing that actually looks like the picture? I drew a blue sky, green grass background, and then a brown tree trunk with dark green leaves... Just all blobs, basically. Not a single one of the pictures had a tree in it. They didn't look ANYTHING like the 'picture' I drew.
  • As usefull as a broken toaster. Only good porn hits will save thee
  • "What are we going to do tonight, Brain?"

    "Same thing we do every night Pinky, try and take over the world! We shall create millions of doodles which will keep the world's intelligence services occupied long enough for us to take over without opposition."
  • It seems like if I do a search by an uploaded file, and I upload (or point to the URL of) an image that I have posted on Flickr, that image should come up first in the list of results, but it doesn't. How are these other pictures better matches to my picture than that picture's duplicate?
  • For a 3D model search engine, princeton has provided a 3d model search engine based on sketches of the three axis aligned planes.

    http://shape.cs.princeton.edu/search.html [princeton.edu]
  • (My group did a content based image search engine at OSU: http://www.cse.ohio-state.edu/~hakan/CIS772/index. html [ohio-state.edu])

    The interesting thing about color is that it is good enough ("Voxel 4" was our best if you find our website) to find images that have been resized, run through *some* effects filters, or rotated.

    So if you use the same usericon etc, resized, on unconnected websites, that could be used to correlate your identities once this feature is in a global search engine. Also, the clustering of related imag
  • Please tell me I'm not the only one who thought Mouse Doodles referred to excrement at first?
  • I worked for Pacific Press Service in Tokyo developing photo copyright and library tech until 94. I first saw a photograph search engine developed by Fujitsu around 92-93 I believe. It required the user to draw the type of image composition very roughly with a mouse and paintbox. So you would draw a horizon line, fill the bottom with blue and draw a yellow circle above if you wanted photos of the sea and sun. No wavelets at that time.

    I then corresponded briefly with Ingrid Daubechies of AT&T who brought
  • I don't see where the article mentions exactly how the "mouse-made doodies" are mined for the energy to power the hack. Possibly by way of methane extraction? Oh, "doodles", not "doodies". Never mind.

What sin has not been committed in the name of efficiency?

Working...