Slashdot Mirror

There are also actual implementations, like this one for Linux.

Try findimagedupes (CLI) for just finding duplicates or imgseek (GUI) for more powerful features. Both even work for images that aren't porn.

There is already an experimental search module that does what you describe - though it searched images in your hard drive only. I remeber seeing it advertised in /. a couple of years ago. Its accuracy leave something to be desired but it worked as proof of concept. The program was open source, I'm sure it'll still be available at freshmeat. Look for image galleries software, you'll find it there (I think it was either KMRML or imgSeek). Now it even has a web version.

Yep, it is called QBIC--query by image content. The web site points to another web site or two that use QBIC for retrieving images from a collection.

Facial recognition is one thing, but if you just want to try to categorize your current collection you might try imgSeek, which is a pretty cool program. Keep in mind that no one has really yet hit upon a great general purpose algorithm for finding matches to images or query by content. There is a large subjective component in categorizing images. If an image is mostly monochromatic blue and it's a picture of a boat, does it get classified as a boat or does it get lumped in with other predominantly blue images? How do you decide whether something is more blue than it is a boat? I suppose at that point a human has to step in to say "I'm really interested in the shape of the object more than I am the color right now."

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 wavelets to the U.S., and was kind enough to send some of her papers. Wavelets are neat because it is like getting a paintbox full of different waveforms, localized as another poster mentions not just a fourier of the entire image. Anyway they are much better known now, so you can find it on the net.

This is not really the same as Barnsley's fractal compression one startup worked on around that time IIRC. They basically had a library of fractals which would be matched to image features, and once you had covered the entire image with them you would be able to zoom into it infinitely, since fractals are self-similar. You wouldn't necessarily get new detail but it would fool you into thinking you were. (I wonder if they liscensed it to anyone). They claimed 400:1 compression, etc. I don't know if they were the basis of LivePicture or if that was wavelet based.

These technologies all have two things in common, which is selecting an algorithmic strategy for talking about images, and storing it so efficiently that the data can be found quickly. The old Fujitsu system ran on a NEWS workstation IIRC, and it was blisteringly fast compared to any system I have ever seen. Only problem is doodles all look pretty much the same unless you are talented and patient.

It seems PNI (Picture Network Interactive)'s natural language recognition text searching for photos was the best, it was just text but used software supposedly developed for the White House. Only thing was they wanted to take over the entire industry with online contracts (this was around 1993) so everyone hated them. Nice tech though.

Anyway, wavelets may not be the entire solution but certainly they are a very useful way to describe data (not just a photo) and undoubtedly have lots of potential applications that just haven't materialized yet. Here's some tidbits Lancaster's links ImgSeek
  Perl Haar decomposition and seeking
  Blitzwave lib
  wvlt
  wvlt #2
  Wavelet.org
  WSQ used for FBI fingerprinting

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.

Since you're interested on social bookmarking and images, you may also be interested on this new site for discovering and rating good images called out.imgSeek.net.

You can tag images you see on the web and retrieve them later. And by rating images, the system learns and will then be able to recommend images you may like. It's also possible to browse images by shape and color similarity.

They are using the image similarity engine from an open source desktop app (http://www.imgseek.net/) also called imgSeek.

Here's an example of similar image search: http://our.imgseek.net/image/show/5250

Since you're interested on social bookmarking and images, you may also be interested on this new site for discovering and rating good images called out.imgSeek.net.

You can tag images you see on the web and retrieve them later. And by rating images, the system learns and will then be able to recommend images you may like. It's also possible to browse images by shape and color similarity.

They are using the image similarity engine from an open source desktop app (http://www.imgseek.net/) also called imgSeek.

Here's an example of similar image search: http://our.imgseek.net/image/show/5250

Since you're interested on social bookmarking and images, you may also be interested on this new site for discovering and rating good images called out.imgSeek.net.

You can tag images you see on the web and retrieve them later. And by rating images, the system learns and will then be able to recommend images you may like. It's also possible to browse images by shape and color similarity.

They are using the image similarity engine from an open source desktop app (http://www.imgseek.net/) also called imgSeek.

Here's an example of similar image search: http://our.imgseek.net/image/show/5250