Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
Science Entertainment Games

Teaching Computers to See with Games 57

Posted by timothy from the playing-doctor dept.
An anonymous reader writes "The Pittsburgh Post-Gazette has a story on Peekaboom, a two-player on-line game in which one player tries to get the other player to guess a word associated with an image, by revealing parts of the image one click at a time. From the article, "The process of revealing objects, or highlighting images within the larger context of the photo, is the sort of thing that researchers in computer vision must do to teach computers to see.""
This discussion has been archived. No new comments can be posted.

Teaching Computers to See with Games More

Teaching Computers to See with Games

Comments Filter:
  • How apt, first five or six attempts to view this got:

    Nothing for you to see here. Please move along. :)

    • Well, I got registered but there is something in some sites that crashes my Mozilla and they have it.

      It seems like worthwhile research. We might learn to recognize things by a process as mundane as actually seeing them from different angles but I suspect there are processes of object abstraction at work as well.

      • Re:Frist? (Score:2, Informative)

        by Ersatz Chickenweed ( 868568 )
        The site works like a champ on my Mozilla (bangbang023). The game is a Java app and requires Sun's JRE 1.4 or later, so perhaps that's what's causing the problem for you.

  • Aka? (Score:1)

    by redmo ( 119229 )
    Also known as Pictionary..
  • ... tell MS about this! Can you imagine?

  • Think of the possibilities! (Score:3, Funny)

    by fmwap ( 686598 ) on Wednesday August 03, 2005 @06:17AM (#13229342) Journal
    I always wanted a computer that could identify my predetermined pr0n fetishes and automatically download accordingly...then I could cut the browsing time in half and get right down to business.
  • Keep going with the science, but I'm revoking your right to name anything. "Peekaboom." Good God.
  • A few weeks ago there was an article about teaching a computer to play chess using a bayesian spam filter. While it was kludge-y, it was a pretty good idea, and had some interesting results.

    Why not try that with vision? Ditch the spam filter and use high-end bayesian analysis, feed the bayesian learning-program all of the data about different objects in a video game who edges are already defined, usually by colors and texture borders, see what you get.

    I'm no expert on this-- can anyone offer ways it could o

    • I'm no expert on this-- can anyone offer ways it could or couldn't work?

      The human eye works in a similar way. The first layer of optic nerve after the retina recognise dots. The next layers recognise contrast and patterns in the previous layers, i.e. lines, edge recognition, etc. By the time it gets to the brain it's already broken down into basic shapes, at which point there are nerves that have been taught to look for certain combinations of shape and colour are triggered, causing the sensation of re

    • Bayesian learning is precisely the kind of thing that AI/ML people do in order to "learn." (There are many others, too.) It isn't even new, but has gotten some slashdot popularity because of the new spam filters.

    • Re:What about Bayesian analysis? (Score:1, Interesting)

      by Anonymous Coward
      You seem to logically following from a set of news story and extrapolating ideas. Unfortunately, the conclusions you are implying are, in actuality, a little backwards. Let me explain. Bayesian filtering wasn't developed to fight spam. It has been around, in theory, a long time before spam filtering, and spam filtering is just one application where it has reached prominence (especially in the Slashdot community). Saying that "a spam filter was used to learn to play chess" is really a misnomer. Bayesian fil

  • Tips (Score:2, Interesting)

    by M3wThr33 ( 310489 )
    Always pick a hint.
    That adds 25 points to your score.

    During the bonus round you get points for clicking the same spot as your teammate. Once numbers start appearing, keep clicking right there for maximum points.

    Pass if the word looks difficult. Don't hesitate.

    Pass if your partner passes, too. He probably has a good reason to.
    • If you get a word that's possibly inappropriate for children (boobs is the mot common one, but also tits, gay, sex, ass, etc), pass immediately. There is a filter that will prevent your partner from guessing these words, but it will still give you pictures labeled with them.

      Seconding the use of labels. They're worth 300 points over the course of a full game. If none of them apply, because, for example, the word is an adjective, select "text". It's the least likely to be misleading to your partner.

      Common

  • The real story today... (Score:3, Interesting)

    by sootman ( 158191 ) on Wednesday August 03, 2005 @06:31AM (#13229370) Homepage Journal
    Teaching, computers, games, yeah, fascinating... so, what's the deal with the moderation here? Why are there so few comments with scores over +3? My default is +5 and the whole front page right now shows *zero* comments at that level. Did they get real stingy with the mod points all of a sudden?

  • end result... (Score:2, Interesting)

    by rd4tech ( 711615 ) *
    Bypassing captchas?
    • Actually, if you look, it's the same researcher who headed up both pieces of work. The whole idea behind CAPCHA is that if someone breaks it, we get some cool piece of technology out of the deal. This certainly counts as cool, but it's explicit labeling -- you still have to run it by actual people to get the labels.

      • Re:end result... (Score:2, Interesting)

        by Anonymous Coward
        Actually, this work is more related to his prior work on the ESP Game, which collected labels for images. The problem after that is that you know an image contains a boy and a dog, but you don't know what is the boy or what is the dog.

        With Peekaboom, you give them the job of guessing "dog", and the parts of the image that are revealed are likely the parts of the image that contain the dog.

        That said, the relationship to CAPTCHAs is still there. Simple image distortion CAPTCHAs don't really hold up, and the

  • Isn't actually being used (Score:3, Insightful)

    by ArbiterOne ( 715233 ) on Wednesday August 03, 2005 @06:56AM (#13229433) Homepage
    The article only says that this technology has the *potential* to help computers to see objects, not that it *is*.
    Quothal:
    The process of revealing objects, or highlighting images within the larger context of the photo, is the sort of thing that researchers in computer vision must do to teach computers to see.

    While the ESP Game was designed to generate descriptive labels for photographs and other images, Peekaboom is intended to help teach computers to see.
    • The summary of the article isn't really very accurate. It's better to see this as a way to get a huge amount of labeled image data quickly--the players label it as a by-product of playing the game. The idea is then that the data set could be used as input to a learning algorithm.

  • But do they learn what we think they learn? (Score:3, Interesting)

    by G4from128k ( 686170 ) on Wednesday August 03, 2005 @07:00AM (#13229442)
    There's an old story from the early neural net image recognition days that seems germane to this. A group of researcher were trying to train an artificial neural net to recognize military tanks that were partially hidden in forested scenes (this was the bad old Cold War days and spotting Soviet tanks in West German forests was the problem du jour). Pictures of natural forested scenes with and without tanks were used to train and test the system. It seemed to work very well on all the training and test data.

    But when they tried the system on more images, it failed miserably. Further investigation revealed that, by accident, all of the "tank" pictures had been taken on cloudy days and all of the non-tank pictures had been taken on sunny days. The system had learned, and learned beautifully, how to recognize cloudy vs. sunny days.

    The point is that the software was good enough to learn to recognize the difference between the two populations of images but that that difference wasn't the one intended by the people working on the system. In the same vein, I'm sure that Peekaboom will learn to distinguish between objects in images but whether it learns the actual object or just some incidental characteristic of that pocture of the object will require a very very good diversity of training pictures to avoid accidental, non-meaningful patterns in the image data.

    I do wish them luck. Perhaps Peekaboom could create a distributed version of the training process in which others can both submit and help train on new objects/images. Letting others submit images and train the system would help diversify the training & testing data sets. Because some people will, no doubt, submit porn, I'm sure the system might become quite adept at recognizing the nether regions of the human body.
    • That is exactly the problem that they are solving. By using a game to collect a data sample instead of a couple of grad students, they can get millions of images labeled instead of hundreds. The more images, the less likely you are to have correlated image features (tank presence and cloudiness were heavily correlated in the neural network system you are recalling). Of course they also run the risk of very poor data, such as someone spelling out the word using cleared space as ink.
  • Fix the damn moderation system!
    No posts at 4+ for a long long time.
    I am not gonna read /. without mod points at low thresholds.
    If you want to vote for it - reply below.

  • No moderation leads to lack of comments (Score:1, Interesting)

    by Anonymous Coward
    In some sense, Slashdot is the ultimate MMORPG. The comments system provides almost immediate feedback in the form of replies and moderation. Most posters can be categorized into some sort of stereotype.

    Some posters like giving lots of information and opinion and getting lots of replies in return. They typically have a little background in what they are discussing, or have a very strong opinion on the subject. When they post and get modded up and have lots of replies, they have achieved a personal victo

  • link to the powerpoint presentation (Score:1, Informative)

    by Anonymous Coward
    http://www.aladdin.cs.cmu.edu/workshops/lamps05/Sl ides/Peekaboom.ppt [cmu.edu]

    the one in google's index now seems to be broken
  • My research involved developing a software system to "learn" a protolanguage of nouns/verbs based on visual perception. Part of the vision system involved having the computer detect "significant" objects & relationships in video frames and tracking similar object/relationships across both different frames & different videos. Here's a short paper [cornell.edu].
  • As a computer vision researcher, I thought I'd share a little insight as to why this is helpful for the computer vision community.

    Whenever one wants to train an algorithm to detect or recognize an object in a data set, one needs both the data set and the ground truth. The data set is usually a large set of images and the ground truth is some semantic information associated with each image, such as the locations of people and cars, or perhaps a representative word or category. The data set is usually ea
  • I am a student at one of CMU's summer programs called Andrew's Leap [cmu.edu] and they gave a presentation on this program to us.

    The premise was that no algorithm existed for computers to be able to find where within a picture a certain object existed. But who is good at doing these things? People. Normally, a group of people would be paid to sort through hundreds of thousands of different images and find where a certain object was. But this was slow, and consumed unnecessary resources (like money). However, the in

  • Maybe 'face' recognition systems could use the same strategy for free research.

Slashdot Top Deals

Top Ten Things Overheard At The ANSI C Draft Committee Meetings: (10) Sorry, but that's too useful.

Close