« 2004/03/17 » 1211 | invention | | The other day I read an article off of slashdot that discussed the problem of websites that stole the content (graphics, links, code, etc) of other websites. Currently, Google is probably your best bet to see if someone has stolen some text from your website. But what if they've taken some graphics and renamed it? How would you ever know? It then occurred to me that Google could make use of that giant image database they have and apply some graphical filters that would enable them to compare the (algorithmic) contents of the images. I was thinking of something along the lines of using the factors of a first pass of a fast fourier compression. Well, ok, more precisely I was thinking of - Compare filesize, filetype.
- Open file, compare dimensions
- Compare first pass, second pass etc
The search would return those images that it deems to be very close, up to some level of tolerance based on the number of passes and the compression strength. Now obviously this doesn't work for images that have been resized or significantly edited. On the other hand, most copycats don't bother changing the copied image anyway.
[Comment on the above] |
| llamatron
If you want to chase people who aren't going to bother altering the images, why not just have google settle on a digital watermarking standard and then build its own database, watching for marked files?
Check out this page for some stuff on issues around monitoring for things like image theft. Hwan (hp)
The difference here would be that images which are similar will also show up (i.e. not necessarily exactly the same).. handy if you, say, wanted to find a bunch of a certain type of picture. I think the results would be very interesting, although I'm uncertain of the usefulness (outside of pr0n foraging). Growl
I'm mostly ignorant here, but won't adding text on top of your stolen image screw up the ID-ing of that image based on FFT? Wait..bitmaps of text would be high-frequency. OK what if I applied a small Gaussian blur to the stolen image? Will that fool your matching software? What about rescaling/resampling?
I would agree with llamatron that watermarking is better (and scale-free, isn't it?) if all you want is to track theft. Auto-foraging for porn is a harder... er more difficult...challenge. too much (hp)
FFT compression is lossy.. so details such as minor text, blurring, face changes can be mostly ignored. It depends entirely on the level and strength of the passes (ie. compression). An analogy would be software that squints (purposefully blurs out details) to gain a quick, general summary image. I suppose this is a challenge for me to write up an engine (I'd call it MagooVision), but graphic libraries involve unsettling math.
|
Recent comments | 2010/08/03 Hwan I won't say that all is well (for I don't believe it to be so), but I am better. Thanks to all for asking!
2010/07/20 QYV Expected range for Creatinine for guys is 60 - 110 umol/L
2010/07/20 llamariffic Hmm, macrocytosis here as well, but to be honest I've had it since before I truly embarked on drinking as a proper hobby. Similarly, stopped drinking entirely, and it didn't go away. Just one of those things, I think.
2010/07/19 girl ack!! It's weird to think that I am now a parental unit. It was nice to see you hwan!
2010/05/21 Hwan I recall trying earplugs well back in my undergrad years, to mixed results. My sleep was troubled by feelings of claustrophobia. I also have a, perhaps unfounded, fear of not hearing the essential alarm in the mornings. However, I may give these another go, thanks.
2010/05/21 llamatron Have you tried sleeping with earplugs? My flat faces out onto a main road, so I've started using the standard foam plugs. It took a few nights to get used to them, but they make a big difference.
2010/05/21 girl The original swedish title: "Men who hate women". I'm not sure if it's the fault of the translation, but I never liked the reporter dude.
2001/03/07 Hwan Damn.. it seems Unweb has since died. http://www.gamegrene.com/node/183
2001/03/07 TY SHARDEL YOU CAN TRADE WITH THE UNIVERSE AND ENABLE SOCIAL NEEDS, OR PERHAPS POST WISH LISTS, HUG THE GLOBE LIKE A BIG OCTOPUS... TY
2010/03/24 Hwan I am amused by the John Irving comparison. http://en.wikipedia.org/wiki/John_Irving#Recurring_themes
|
|