Slashdot Mirror
An Advance In Image Recognition Software
Roland Piquepaille alerts us to work by US and Israeli researchers who have developed software that can identify the subject of an image characterized using only 256 to 1024 bits of data. The researchers said this "could lead to great advances in the automated identification of online images and, ultimately, provide a basis for computers to see like humans do." As an example, they've picked up about 13 million images from the Web and stored them in a searchable database of just 600 MB, making it possible to search for similar pictures through millions of images in less than a second on a typical PC. The lead researcher, MIT's Antonio Torralba, will be presenting the research next month at a conference on Computer Vision and Pattern Recognition.
This will be used to break CAPTCHA-type schemes even worse than they already are.
cue conspiracy theory about online censorship
thank god, now i can get some assistance when i'm taking one of those "real tits or fake tits" online quizes. fapfapafap.
Now the spammers have an automated "captcha" breaker. As if taking advantage of social behaviors wasn't enough. On the plus side, though, it's going to improve the efficiency of porn searches dramatically. :)
...I'll believe it when I see it.
Until then, it's snake oil, as far as I'm concerned.
Perl - $Just @when->$you ${thought} s/yn/tax/ &couldn\'t %get $worse;
If I read you correctly - and I think I do... You mean to say that snake oil is somehow... invisible?
No wonder those snakes are not only so quiet, but I never even see 'em coming!
Geez. We don't stand a chance.
"Flyin' in just a sweet place,
Never been known to fail..."
.... the answer is always "a picture"
I hate reading press releases of reading papers with real explanations of what's going on.
I just finished reading "Small Codes and Large Image Databases for Recognition" written by the guy. All he did was implemented Geoff Hinton's idea of databasing images with a binarized coefficients produced by Restricted Boltzmann Machines.
Hinton himself gave a talk on it for Google here:
http://www.youtube.com/watch?v=AyzOUbkUf3M
Actually I'm wondering, is he plagiarizing Hinton?
-- Making computers see, hear, and think... http://www.componica.com/
I guess nobody there thought to do the math before making these claims. This story probably shouldn't have made it to the front page; it's less than useful.
This is not so much an "advance", and more a demonstration that some image recognition problems can be solved with fairly simple, well known methods and a lot of data.
all the Obama halloween masks setting off false positives from sea to shining sea.
I regret that I only have one mod point to give per post.
a fake ufo picture and a real one?
How will spammers make use of this? Well just make that viagra pill be reflected in a coke bottle.
anyone for a random bit generator to see what random results gets labeled?
Wonder what fractals might produce?
moral of the question: we can always break what we make.
... unless he means they produce the same output from his algorithm....
Oh my, the soon to be most searched "name" on the web is... Jenna Jameson! Wait a minute, I think I misunderstood "facial" recognition...
Sig Registration Form 34c_766(a) submitted to Ministry of Signature Management. Approval pending.
if they grabbed 13 million images from the net, there's a good chance that many of them are copyrighted. if they are using those copyrighted images in their (presumably FOR SALE) software, wouldn't that require some serious licensing fees, even if it's an internal-you-never-see-the-pictures usage, since it's a part of their algorithm, or what-have-you?
for the record, i say this as a concerned/curious artist who isn't looking for a payout.
Seems like this doesn't actually identify the picture using the 256 bites, but simply matches them against a database filled with 256 bites from other pictures, which means your sucess depends on whether you have a subject in your database that's a good match. Sounds like someone writing yet another bruteforce "algorithm" for a complex problem, which doesn't actually solve the problem, but simpel works nice in a testenvironment, where a flower is matched against a couple of thousands of flowers, and yields a slight match.
Given this works under real world conditions, it would make it possible that every shop gets the list of faces of criminals or other people which "you dont want" in your shop, recognize them in real time using little investment only and throw them out. Or the possibility to track a person on traffic surveillance cameras. That is pretty freaky. Politicians, please make laws which restrict such databases. I don't like the idea of beiing escorted out of the shopping mall because of my credit rating. Or that some idiot at the pollice marks me as suspect because of my moving patterns (which can be easily saved for a long time). Imagine that he can select you and then track you more or less in real time.
If surveillance is to cheap it becomes a problem....
1984 here we come!
Or rather... I'll believe it when it sees me!
No, I think the parent is making a joke, something about recognizing the advance in recognition, when the advances become recognizably advanced or apparent... I reckon.
This actually solves a problem I've been stumped on for a while. I need a way to search for similar images such that images that are similar have a searchable value with an inherent "nearness" quality.
That is, there are a number of image similarity algorithms, but the computed values of two similar images are not necessarily mathematically near to each other. This algorithm produces values that are, which can make searching for similar images among very many images, quite fast.
I hope they didn't use any of my pictures because I sure as hell didn't give them permission to use my images for something like that and I clearly state that my own work is my property on my website for my use only.
While I don't care about most uses about my images (go a head and PS a penis in my mouth) but I would fight it if I found out it was used for this.
The actual paper is at http://people.csail.mit.edu/torralba/publications/nipsRecognitionBySceneAlignment.pdf
From what I can tell, it's basically, "blur the image down to only a few hundred pixels and then you have less data to comb through!"
Yep, I second that. The article is really short on details. Not surprising since they're presenting it at a conference next month. We don't even know what kind of features they are extracting from the images. Are they using wavelets? Texture descriptors? Color information? Shape recognition? It sounds like a combination of true content based image recognition with keyword input association if I read the article correctly.
If they are claiming to have a general image recognition algorithm that'd be something. As it is a lot of research goes into recognizing specific kinds of things, such as faces, license plates, etc. I'm very curious to see what they've come up with.
http://www.rootstrikers.org/
Even if this was perfectly efficient, I'm pretty sure there's more than 256 * 1024 things you could have an image of out there. The amount of information this analysis could give just can't be very useful.
Thats not meant to disparage the work - image recognition is important and difficult. This particular 'advance' just isn't that 'advancing'
A convenient way to automatically sort all of my porn.
Read the papers then
http://people.csail.mit.edu/torralba/tinyimages/
But then again, rotating an image 90 degrees might defeat the whole system. Scientists are so busy being sophisticated and racing to write journal articles that they often miss the obvious.
...I'll believe it when I see it.It'll believe you when it sees you.
Of course that typical PC is a dual quad-core machine running at 3GHz with 8GB of memory, GPU X3 running offloading co-processing software, and 1TB of hard drive space.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Does it means that http://images.google.com/images?gbv=2&hl=en&q=pamela+naked&btnG=Search+Images will soon return not only pictures from pages with the specific keywords searched? Neat!
As I understood it, it's not for sale, you can get it at his MIT website
Another Roland Piquepaille story on Slashdot. He is paid to get stories on the internet. Does he pay Slashdot?
The PDF linked to is named "nipsrecognitionbysciencealignment.pdf"
So... the are using it to identify nipples?
http://people.csail.mit.edu/torralba/tinyimages/ Anyone actually look through any of these? I've noticed some... imperfections. More instance, under "greenweed" you can find a picture of a dog on a map of the US. There's also a few pictures that are actually green weeds, but not enough to counter out these two exceptions.
Works better if you have good smoke
What?
Jump down, turn around,
Pick a bale of hay.
"Flyin' in just a sweet place,
Never been known to fail..."
...I'll believe it when I see it. Exactly. This is a routine rite of passage for all Pattern Recognition researchers: when they need to justify more funding, they claim to be "just around the corner", hence we have this type of hyperbole. The paper is ridiculously simplistic, and does not deserveThis technology has been around for centuries! 256 bits to describe the content of an image? It's called title. 1024 bits to describe the content of an image? It's called a caption.
Check out libpuzzle : http://libpuzzle.pureftpd.org/project/libpuzzle
It's also designed to quickly find similar images, even out of millions of images. The documentation describes a possible indexation technique (as suggested in the original paper):
http://download.pureftpd.org/pub/pure-ftpd/misc/libpuzzle/doc/README
Images are stored as 544-bits signatures by default.
{{.sig}}
...are of Phuket.
...Lorenzo / I'm into kinky crustaceans. I just discovered internet praWn.