Slashdot Mirror

← Back to Stories (view on slashdot.org)

New Algorithms Improve Image Search

Posted by ryuzaki0 on from the where's-waldo dept.

bc90021 writes "Electrical engineers from UC San Diego are making progress on an image search engine that analyzes the images themselves. At the core of this Supervised Multiclass Labeling system is a set of simple yet powerful algorithms developed at UCSD. Once you train the system (the 'supervised' part), you can set it loose on a database of unlabeled images. The system calculates the probability that various objects it has been trained to recognize are present, and labels the images accordingly. After labeling, images can be retrieved via keyword searches. Accuracy of the UCSD system has outpaced that of other content-based image labeling and retrieval systems in the literature. One of the co-authors works at Google, where the researchers have access to image collections at the largest of scales."

28 of 111 comments (clear)

  1. when I was your age by Anonymous Coward · · Score: 5, Funny

    I remember when we had to go to a gas station and *buy* porn. Now you have computers out there finding porn for you. You kids today have it too easy!

    1. Re:when I was your age by Prysorra · · Score: 2, Interesting

      That's one of the famous uses of image analysis - finding the presence of human skin in digital pictures.

      Skin detection.....5.5 million hits on Google.

      Once you can do this accurately, companies like McAffee and Norton can scan the internet and database pr0n sites for the whole web. Keep in mind that there's a subscription service that allows a Norton database to filter websites for them.

      Parents...

    2. Re:when I was your age by PPH · · Score: 3, Funny

      They chose the wrong name. It should have been "Supervised MUlticlass Tagging" or SMUT.

      --
      Have gnu, will travel.
  2. Cool! by Deagol · · Score: 3, Interesting
    If this doesn't revolutionize the searching of online porn galleries, I don't know what will. :)

    Snarkiness aside, this is pretty cool stuff. I hope to see usable OSS code in a few years. Imagine how cool it would be to query "show me all pics with my daughter and her rabbits" and have it week through the 1000's of digital family photos.

    --
    Method of processing duck feet
    1. Re:Cool! by Cheapy · · Score: 5, Funny

      I find it disturbing that you combine porn, your daughter, and rabbits all in your post.

      You have issues.

      --
      Would you kindly mod me +1 insightful?
    2. Re:Cool! by UbuntuDupe · · Score: 2, Interesting

      Correct me if I'm wrong, and I'd like to be wrong, but isn't this (just) another application of Bayesian logic like is done for spam? They have some kind of way of quantifying the image in a number of variables and then use training to match certain variable values to a search term.

      (Even if it is, I don't want to trivialize the road from theory to practice, I just want to know what's different.)

      I did something a little while ago where I had a program search through text, and for all occurrences of all n-character strings (where you choose n) appearing, it would gather the information about how often each other character comes after each string appearing in the text. Then you'd give it an n-character string and it would use those probabilities to generate a new body of text. It was cool, even if it generated complete garbage except for large n.

      I hope to see usable OSS code in a few years.

      You mean for this algorithm, or at all?

      --
      Apology to Ubuntu forum.
    3. Re:Cool! by Tackhead · · Score: 4, Funny
      > If this doesn't revolutionize the searching of online porn galleries, I don't know what will. :)
      >
      > Snarkiness aside, this is pretty cool stuff. I hope to see usable OSS code in a few years. Imagine how cool it would be to query "show me all pics with my daughter and her rabbits" and have it week through the 1000's of digital family photos.

      ...the coolness of which is directly proportional to hotness of your daughter, the hotness of whom must then be further weighted by multiplying her hotness by some function of her age. The age-multiplier curve features an abrupt discontinuity that jumps 0.00 to 1.00 at age 18, and some sort of exponential backoff function that starts decreasing the multiplier at around age 35-45.

      But apart from the fact that it's almost Easter, what's with the rabbits? *clickity clic*-hey, I didn't know you could do that with Cadbury easter creme eggs!

      (Rule #34: There is porn of it. No exceptions.)

    4. Re:Cool! by andphi · · Score: 2, Funny

      I was going to assume that his daughter is little and likes rabbits because they're cute and fuzzy, or that she's somewhat older and keeps rabbits because they're cute, fuzzy, and more manageable than other animals. But, sadly this is Slashdot, so images that contain girls but aren't pr0n are apparently incomprehensible.

    5. Re:Cool! by Anonymous Coward · · Score: 5, Funny
      > But, sadly this is Slashdot, so images that contain girls but aren't pr0n are apparently incomprehensible.

      Fortunately, this is Slashdot, so discussions of pr0n that don't feature square-waves, multipliers, and exponential backoff functions are apparently incomprehensible too!

      (What are these "girls" of which you speak? I only remember Millie Amp... she was imaginary, skinny as a wire, but when her insulation got stripped, she stopped resisting, got really hot, and started to moan "ohm, ohm, ohm"?)

    6. Re:Cool! by andphi · · Score: 4, Funny

      By 'girls', I mean the limiting reagent in human reproduction. As a class of compounds, 'girls' are extremely common but somewhat volatile, so creating bonds with them is sometimes difficult. They are attracted to other similarly elusive compounds. Examples of these attracting compounds include 'Time', 'emotional vulnerability', and 'financial stability'.

    7. Re:Cool! by hoggoth · · Score: 2, Interesting

      > ...the coolness of which is directly proportional to hotness of your daughter, the hotness of whom must then be further weighted by multiplying her hotness by some function of her age. The age-multiplier curve features an abrupt discontinuity that jumps 0.00 to 1.00 at age 18, and some sort of exponential backoff function that starts decreasing the multiplier at around age 35-45.

      Hotness = BeautyFactor * SexyFactor * AgeHotnesseAdjustment
      AgeHotnessAdjustment = cos(2*(Age-18)/3.14159)

      Gives you maximum hotness at 18, falling slowly in the 20's, dropping rapidly after that.
      Also, some hotness under 18 (lets be realistic!) , but not too far under 18

      --
      - For the complete works of Shakespeare: cat /dev/random (may take some time)
    8. Re:Cool! by crawly · · Score: 2, Interesting

      Umm no, that isn't what you want at all, that would give you a pretty horrible periodic function.

      Try something like this
      if age<18: AgeHotnessAdjustment = 0
      else: AgeHotnessAdjustment = 1/exp((Age-18)/20)

      --
      GCS/S d-x s+(+): a C++++$ UL+$ P+ L++$ !E--- W++@ N++>$ !o !K-- w++$ !O !M !V PS++>$ PE !Y PGP+ t+ 5++ X++ R tv b
  3. so how does this ... by sarathmenon · · Score: 4, Funny

    change the way I search for Natalie Portman p0rn?

    --
    Microsoft: "You've got questions. We've got dancing paperclips."
  4. Probability by DoofusOfDeath · · Score: 3, Interesting

    The system calculates the probability that various objects it has been trained to recognize are present,

    The probability is either zero or one, because whether or not the feature being sought is present is a state of nature. It would be more helpful to call this number the confidence that the feature is present.

    1. Re:Probability by AnonymousCactus · · Score: 2, Informative

      The probability isn't zero or one because the system doesn't have perfect knowledge and the probability is with respect to what the system 'knows'. Probability here is estimated based on the limited representation of the algorithm, so it's saying that based on the things I've seen before with similar features that were labeled 'tiger', X% were labeled 'tiger.' I would then expect this new thing to be a 'tiger' with a probability of X. (Exactly how they come up with their estimate is a bit more complicated :)) Confidence is a reasonable way of describing what that probability represents, but it's correct to say probability.

    2. Re:Probability by Anonymous Coward · · Score: 4, Insightful

      Not if it is a Bayesian probability.

    3. Re:Probability by $RANDOMLUSER · · Score: 4, Funny

      You're not big on quantum superpositioning I take it.
      I can take it or leave it.
      --
      No folly is more costly than the folly of intolerant idealism. - Winston Churchill
    4. Re:Probability by timeOday · · Score: 4, Interesting
      Or a fuzzy set, as (virtually) all set in the real world are.

      For instance, the set of pictures for which the statement "is this a picture of a chair" is true. There is no objective criteria for this. So imagine you have a bunch of pictures and show each one to a thousand people. Sometimes you might get 0 or 1000 "yes" responses, but often you'll get some number in between (because there are chairs, but barely visible, the picture includes a kids booster seat, or a rock big enough to sit on). This could be interpreted as a probability that somebody will consider a picture to be of a chair.

    5. Re:Probability by emlyncorrin · · Score: 4, Funny

      You're not big on quantum superpositioning I take it.
      I can take it or leave it. I can take it and leave it!
  5. A military system I saw on a TV program ... by Anonymous Coward · · Score: 5, Interesting

    ... was similarly trained to recognise tanks in landscapes. I was doing really well - getting a great score on the fresh images it was presented with.

    Then they introduced it to a new batch of images and it fell apart.

    Turns out that the initial set of images had all the tanks shot on a sunny day and all the tankless images shot on a cloudy day (or vice versa). It had learned to tell a sunny day from a cloudy day.

    Ha ha.

    1. Re:A military system I saw on a TV program ... by ClosedSource · · Score: 4, Insightful

      The system used neural nets. Generally you try NN's when you don't really understand the problem well enough to try a conventional approach. The problem with NN's is you really don't know what they are actually "learning".

  6. Why is it better? by AnonymousCactus · · Score: 2, Informative

    I wish the article would mention more about why it is better than similar techniques that have been proposed in the past. (For example, http://luthuli.cs.uiuc.edu/~daf/papers/WAP-fin.pdf seems similar) For instance, where do they get their labels for the training data? A lot of people have tried using contextual words drawn from surrounding web text to limited success due to noise. It's also questionable how well their techniques can do if they need to pre-build a separate classification for each keyword. Finally, there are words that it seems impossible that they could ever distinguish. For example, 'man' vs. 'woman,' would be incredibly complicated for anything but a human. Where are the details? Oh yeah, it's a news story! Here's a link to the paper http://www.svcl.ucsd.edu/publications/journal/2007 /pami/pami07-semantics.pdf

    1. Re:Why is it better? by nietpiet · · Score: 5, Informative

      I find it interesting which ones of the object-recognition and scene categorization algorithms make it to Slashdot.
      Why does this one make it?
      This is a very hot research topic at the moment.
      to name a couple of groups:

      http://www.robots.ox.ac.uk/~vgg/
      http://lear.inrialpes.fr/
      http://www.vision.caltech.edu/
      http://www.science.uva.nl/research/isla/
      http://www.cdvp.dcu.ie/
      http://www.informedia.cs.cmu.edu/
      http://www.research.ibm.com/slam/
      http://www.ee.columbia.edu/ln/dvmm/newResearch.htm

      oh, and people should not stare themselves blind on the claimed results.
      Research papers *always* have to present good results, or else you do not get published.
      Furthermore, these images are of a very high quality, make by professional photographers.
      Many algorithms perform very well on these ('corel'-like) sets, while utterly failing if applied on real-world data:
      http://www-nlpir.nist.gov/projects/trecvid/

  7. The problem is... by Life700MB · · Score: 4, Funny


    The problem is we all know what's gonna be the first result when searching "Caves on uranus"!!!

    --
    Great hosting 200GB Storage, 2_TB_ bandwidth, php, mysql, ssh, $7.95

  8. The tech isn't mature enough yet by The+Orange+Mage · · Score: 4, Funny

    Run this story again when the system can tell the difference between D, DD, and DDD. Bonus points if it can handle "higher" criteria.

  9. Parent not just funny by EmbeddedJanitor · · Score: 4, Interesting

    Since a huge % (perhaps most) image searches are for porn, it is probably a worthwhile thing for a search server to quickly classify likely porn as a way to reduce search server loading.

    --
    Engineering is the art of compromise.
  10. Using games to get lots of tags by lukeinusa · · Score: 2, Insightful

    One complaint about this work is that it requires tagging an initial set of images that are needed to train the system. Vasconcelos' work uses the academic standard "Corel" dataset of labeled images but also uses tagged images from Flickr to train the system. Using human computation games like the ESP game for images and ListenGame www.listengame.orgfor audio, collecting data is not as tough as it once was...

  11. How Many Non-techies Think This Isn't New? by wallywam1 · · Score: 2, Insightful
    It alwasy cracks me up on TV how they show a fingerprint or face recognition system searching for matches. The camera cuts to a computer that's looping away through a bunch of pictures until a match is found. Admittedly, I don't know all of the details, but obviously current systems must have some sort of indexed data points that are entered in a database and then you run queries against the database for potential matches.

    It's a little more plausible now that broadband is readily available but this has been portrayed on TV for years. Can you imagine some podunk field office connecting to an FBI database through a dialup and downloading high resolution images until they found just the right one? Then again, that would make for some good entertainment. Detective walks in..."I've got good news and bad news. The good news is we found the killer. The bad news is, he died of old age."