Automatic Image Tagging 123
bignickel writes "Researchers at Penn State have applied for a patent on software that automatically recognizes objects in photos and tags them accordingly. The 'Automatic Linguistic Indexing of Pictures Real-Time' software (catchy name) trained a database using tens of thousands of images, and new images have 15 tags suggested based on comparisons with objects or concepts in the database. Not sure how you identify a 'concept,' and they're only talking about having one correct tag in the top 15, but still cool."
Not shockingly... (Score:5, Funny)
Re: (Score:2)
Re: (Score:1)
That Sucks (Score:2, Funny)
Re: (Score:2)
There is a way to document prior art. It's called a journal.
These are not defensive patents. They're designed solely to make the uni money. The problem? They made those patents with your tax dollars [at least the public unis]. So you have a public institution telling you that you can't use an algorithm or idea because they took YOUR money and patented it.
Tom
Re: (Score:2)
Arguably, this would be like takin
Re: (Score:2)
The POINT of a uni is to train/educate and THEN PROMOTE FURTHER DEVELOPMENT. That's the point of your PhD is to add something new to the field.
If I'm paying you to develop science for society [e.g. a good thing] and then you rob society of the use of your idea then what's the point? Oh in 20 years society will benefit of it
I wouldn't have a problem if a gang of grad stude
Re: (Score:1)
Re: (Score:2, Informative)
-Nyb
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
from http://www.psu.edu/ur/about/character.html [psu.edu]
Inter
Re: (Score:1)
All that said, I think software patents suck, no matter who is doing the patenting.
Re: (Score:1)
Regarding the compensation levels, Penn State receives less than the other 'state-affiliated' private universities in PA (though my info is somewhat dated).
And I agree with your statement about the software patents, though I think
And EULAs suck, but linux has one!
Re: (Score:1)
Re: (Score:1)
The other 50% is the problem (Score:3, Informative)
I've seen lots of systems like this. The problem is in the 50% of the images that don't work, so basically you have to manually tag 50% of your images.
I saw an interesting one about 10 years ago. It took an X-Ray image, did an edge detection, converted all the edges to a slope vs distance 2D plot, and conerted edge curves to a radius and distance plot, then used a kind of statistical correlation algorithm to pick which part of the body the image was from. I could imagine that you could apply something similar to the luminance of an image to pick out objects, and then maybe do some color transforms and stuff to improve results. The article says they do it in 1.4 seconds per image though, which is impressive.
Re: (Score:3, Insightful)
Re: (Score:1)
Re: (Score:2)
That is because the coarse approach to the problem is relatively uncomplicated, and after building some framework and inputting some reference data it is easy to make the system do some things right. Like guessing keywords correct for 50% of the input.
What is hard is to get it correct for close to 100% of
Re: (Score:2)
XRay much easier though (Score:3, Informative)
In the real world we have an object you might take a picture of from any angle, using a myriad of focal lengths, with variable levels of distorition depending on the lens and camera used. Really nasty for generic object recognition. I think the best we can hope for i
Re: (Score:2)
Don't forget occlusion!
Great point! (Score:1)
Yes, the real world has poles and fences.
Prior art? (Score:2)
http://www.relle.co.uk/papers/2003-Content_Based_
We didn't have enough time to train the system properly, but itstarted off well...
Re: (Score:1)
The science in your 'prior art' is mostly segmentation, and has very limited validation.
If you say Kobus Barnard's work has prior art, that is true, because his work is very related to the ALIP system.
see http://kobus.ca/research/talks/INRIA-02/index.html [kobus.ca]
Re: (Score:1)
LIPS (Score:1)
Re: (Score:2)
cunning linguists
That's disgusting.
Re: (Score:3, Funny)
That's disgusting."
Actually, if done well, it's quite pleasant for all involved.
Re: (Score:3, Funny)
Google, others doing similar research? (Score:2)
Re: (Score:2)
A video an the subject (Score:2, Informative)
View the video on Human Computation [google.com]
Re: (Score:1)
Re: (Score:2)
retrievr (Score:1)
Re: (Score:1)
Nobody is impressed by this (Score:1)
Re: (Score:1)
building city modern historical architecture people ocean_animal fish sub_sea water space cyber art ocean sport
Only one "suggested" tag is relevant. Too bad so much time and effort went into such a waste of time and effort.
Re: (Score:1)
No kidding... How about "pixels"?
I swear I saw a butterfly (Score:2)
API (Score:1)
Re: (Score:2)
Re: (Score:1)
Make sure to check back tomorrow to be able to search based on the tags that the computer suggests, people verify, and ones that people enter manually. I just got all the cron jobs working together.
1 out of 15 ? impressive (Score:2)
(yes, assuming a normal distribution of 'concepts' in the pictures, etc)
Re: (Score:1)
I hate to be a hater. . . but firstly, I doubt any sort of Gaussian or even mixture of Gaussians will work well to describe the distribution of picture labels. And secondly, you get a 50% average by making guesses about an even Bernoulli distribution, like a coin flip.
Re: (Score:2, Insightful)
How do you get that 50% is average on guessing? Their tag pool contains 332 "concepts", which means that randomly picking 15 would give you about 1/22 chance of getting a correct tag for a picture that is tagged with one word. For a two-tag image, you get 1/11. To get up to 50% you'd have to work with images tagged with four or five words. Did I miss something here? Besides, the claim is that "in 98 per cent of tests suggests at
w00t!!! (Score:3, Funny)
That's cool, the rest of it will be like opening xmas presents!
*file: 123456.jpeg>open>Aghh! Goatse!*
Hmmm...This may be neat when it gets a LITTLE more accurate, but a cool start none the less.
Kudus to the gang for getting a grip on a hard problem...erm..nevermind.
Re: (Score:2, Funny)
Re: (Score:2)
Re: (Score:1)
Tags: Disgusting, small, horrifying, triceratops, Grenada
Three out of five ain't bad.
Re: (Score:2)
Okay, I get the first three, but tricerotops aand Grenada? (disclaimer: I trained Spl Forces teams to go into Grenada- and yes, it WAS as fscked up as you might have heard!- so I may have a whole different point of view/perspective about Grenada than you may have
I'm intrigued, especially about the tricerotops, and would appreciate an explaination if you would be so kind.
(no sarcasm intended or implied- I'm really curious!)
Re: (Score:1)
In future news... (Score:1)
Re: (Score:2)
If the algorithm can recognize it in order to find it, it can do so in order to block it too.
IBM was working on this years ago... (Score:2)
Not sure how far they got, but remember reading that IBM was working on this and had some reasonable success at object recognition in images. I'd love to be able to classify the 10k digital images I've got around. Especially if it can recognize individuals (not that it would know their names initially, but would be trainable).
Re: (Score:2)
Re: (Score:2)
Facial recognition is one thing, but if you just want to try to categorize your current collection you might try imgSeek [imgseek.net], 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
Re: (Score:2)
I think I've had it with Slashdot. Too many people like you.
Reportedly (Score:3, Funny)
The system has clearly been let crawl the web for far too long.
Re: (Score:1)
Google will buy it... (Score:1)
Unless Jupiter Media [jupitermedia.com] gets to it first.
Someone like myself would understand the hours of data-entry and database development that goes into indexing imagery. I research photo copyrights for a living.
The fact that there is a feasible, automated system that can do the work will certainly cut down the man-hours for that sort of work; at least by half.
Pity, though. I heard that Google and others had a telecommuting thing that paid people to recognize what's in a photo. Sorry to hear they'll be out of a job
Workarounds....... (Score:1)
Seriously now, I am sure their are people out there that have already got ideas rolling around in their heads about how they can use this technology to hijack images to their advantage. Once somebody understands how the techno
Re: (Score:1)
One tag in 15 correct (Score:1)
image spam filtering (Score:2)
Uni assignment (Score:1)
I'm not... (Score:2)
... usually a pedant... but you don't train a database. It was likely a neural net, but TFA is rather thin on details. Anyone got a link to their paper?
Lots of implications for Surveillance, however. (Score:1, Interesting)
Is there a "Big Brother" category on Slashdot, yet?
Wrong approach? (Score:2)
Well I sure hope they invented it before early 80s (Score:1)
So they say... (Score:2)
Bullshit Patents (Score:2)
Re: (Score:1)
Re: (Score:3, Insightful)
confucius says... (Score:1)
And that's one of the problems: does an image define the taxonomy or taxonomy defines the image [type]?
When it's going to be on Flickr? (Score:1)
Neural Nets (Score:2, Insightful)
That's like patenting training a dog to fetch a stick, it's completely rediculous.
You take software capable of generalizing a neural network algorithm by feeding it pictures and associating each picture with certain tags. It then creates a generalized algorithm model based on what you fed it initially. So that when you give new input it is capable of outputting tags most similar to what you initially trained it.
So yes this software can recogn
Publications (Score:1)
Main publications:
http://infolab.stanford.edu/~wangz/project/imsearc h/ALIP/ACMMM06/ [stanford.edu]
http://www-db.stanford.edu/~wangz/project/imsearch
http://www-db.stanford.edu/~wangz/project/imsearch
unimpressing (Score:2)
There's a few subjects that are so common that it's more or less a given they'll be in a large fraction of the photos. Outputting "people, buildings, nature, animals, plants, city" would probably give atleast 1-2 "correct" tags for 90% of whats in
link? (Score:2)
Pictionary! (Score:1)
MOD PARENT FUNNY! Re:Pictionary! (Score:1)
I wish I had mod points.
Big deal (Score:2)
Move along to real research.
wonder how this compares (Score:2)
I haven't RTFA and I don't have any experience with Riya either, so consider the above posting a waste of time (if you must).
Very important... (Score:1)
Wouldn't it be easier... (Score:2)
Re: (Score:2)