Slashdot Mirror
Computers With Opinions On Visual Aesthetics
photoenthusiast writes "Penn State researchers launched a new online photo-rating system, code named Acquine (Aesthetic Quality Inference Engine), for automatically determining the aesthetic value of a photo. Users can upload their own photographs for an instant Acquine rating, a score from zero to 100. The system learns to associate extracted visual characteristics with the way humans rate photos based on a lot of previously-rated photographs. It is designed for color natural photographic pictures. Technical publications reveal how Acquine works."
Oh great, now we'll turn our computer on in the morning, and it will say "I think this is far too early!" and switch itself back off.
This post was made in complete sincere seriousity; as such any attempts to derive humour are doomed to instant failure.
I'am afraid I cannot do that Dave.
Isn't aesthetic value a hugely personal thing? I mean I looked at some of the photos on the site and the ratings were arse-backwards as far as I was concerned. Generic, boring and frankly badly composed images were getting ~95%, whereas others that I thought were truely exceptional were being ranked in the 50's.
I'm not saying "my opinion is better", just that it seems sort of pointless to assign a value to a picture like this.
You can advertise in this sig from as little as £99.99 a month!
It's terrible. Awful. A hopeless system. I wouldn't use ever it.
And I'm not just saying that because it rated a couple of my photos as poor. :)
http://twitter.com/onion2k
Post Quality Inference Engine for Slashdot. No more mods.
Set your phasers on "funky"!
This seems a little far-fetched considering the vagueness of someone liking a photo that another person doesn't. I can't imagine this on something like flickr. I guess this could be some standalone rating that people could use on stock photography sites, where buying something needs to have commercial appeal. Websites such as alamy.com tend to do these things manually, they probably might find some use for this.
Real men read Slashdot articles at -1, bottom up.
From the Acquine website "A rule of thumb is that if the aesthetic quality of a photo is obvious to most people, it may not be worthwhile to seek Acquine's opinion on it because Acquine may assign funny scores in such cases." So in cases where the correct score is obvious, Acquine's score can't be trusted? That rather neatly avoids validation or refutation of Acquine's results. This is suspicious and seems to cast doubt on the trustworthiness of its score in less obvious cases.
Is that this sort of thing is the dumbest ever, and is bad for the field of AI, where some people are trying to do real work.
What exactly is a "color professional photograph"? Landscapes? Portraits? Group shots? Sports photography? Photo journalism? Abstracts? Artistic Nudes?
This may be an interesting programming toy but it has little to no use in the real world, unless you have a desire to locate generically boring pictures built to formula. (or, generically boring pictures that have been run through the "ALIPR Picture Score Optimizer" Photoshop filter)
-1 Caprine
Set your phasers on "funky"!
It prefers a nazi germany flag over some beautiful landscapes and portraits
my name is godwin and I approve this message
This is great news, a system to tell us whether a photograph is beautiful or not. We are approaching the point where we can outsource all our thinking to computers. Soon we won't have to use our brains at all!
(Not that many of us do presently, anyway.)
Just google image search for any Pulitzer Prize winning photo and upload it to the Penn State ACQUINE system and see how some of them fare to the Goatse image...
The Iwo Jima flag raising photo at this URL gets a 26.1 in the system.
http://surreality.info/up/WW2_Iwo_Jima_flag_raising.jpg
The fucking Goatse image with a construction crane photoshopped into it (don't ask) just got an 84.1 on the same ACQUINE system....and no I'm not going to provide a URL just test it yourself.
So Goate is a better image than the Iwo Jima flag raising photo?
Am I missing something?
Howcome Geek's allwyas try to find matematical patterns to explayn what they can't?
How do I saw goats?
In other, unrelated news, Penn State researchers have released an online image voting system called 'Aesthetic or not' where users are presented with a random image and have to give it a score of between 0 and 100.
Initial user participation was good until for some completely unknown reason, 90% of images presented to users for rating were goatse, tubgirl, or other shock images.
I tried the system, using a high dynamic range pano that I'm very satisfied with, and which has received a bit of praise from other photographers:
http://norloff.org/pano/mirror5x3medium.jpg
According to the computer this image is worth 28.1 points.
I guess this means that either the image is a lot worse than I believed, or the rating system has problems with it. :-)
Terje
"almost all programming can be viewed as an exercise in caching"
Now I don't Have to look at so much porn to find the pics I want to look at.
I've just run a few of my photos, which are on several photo sharing/critique sites and the results seem fairly similar.
Most of the ones I like it scores low, ones I think are formulaic and generic seem to score highly...
If they could adapt it to add random 'nice shot' and 'what settings did you use?' type comments to each image I'd say you could replace most of the photo sites on the web with it and no one would even notice!
A vaguely interesting waste of 5 minutes, but limited real use as it take no account of mood, subject, situation or any of the other things that help define a 'good' photo.
Voting has nothing to do with aesthetics. The beauty of a photo, painting is not some sort of pixel correlation algorithm it is how humans interpret the image and how they eventually FEEL about it.
Right... so u can basically set up a botnet to skew the system...
Or Professor Oak may use your picture in his Pokemon Report
No kidding, I tried it with the url http://www.goatse.fr/hello.jpg and got 76.1
I see Slashdot at work here. Well, I also clicked in the rightmost star in the "How do you rate its Aesthetic Quality", of course...
Hokusai's Great Wave off the Coast of Kanagawa... 15.0 points! I say this bit of software stinks. Nice try people, but it's no good. For the terminally bored, feed it the pictures from HaveYouSeenThisMan.com and see what it says. Oh, for reference, the pic I used:
http://www.globalsecurity.org/eye/images/greatwave.jpg
I wonder how well it fares with images of ladyboys?
Good thing the software wasn't designed to vote. It gave a picture of Obama a rating of 63.7 and a rating of 84.8 to McCain
One thing first. There *are* certain esthetic and technical rules / guidelines which are what we could call "objective" in the sense that they are very general. For example, a photograph usually looks better if the composition is balanced, if the 2/3rd (or golden mean) rule is used, the lines in the picture are coherent and lead the eye in the right direction (e.g. towards the subject), if the photograph is correctly exposed, colors matched etc. Of course, some of the greatest photographs break those rules; however, like in many things, you succeed in breaking the rules if you know what you are doing, and you cannot do it very often.
I can imagine that you can come up with an engine that is able to detect how "rule conformant" a given picture is.
However, pure formal esthetic judgement is what we rarely mean when talking about a "good photograph".
There is one main issue that will make it very hard to match our "overall" esthetic sense. Firstly, we are unable to detach the image contents from the "pure form". That means, if we see a worried women holding a child, we cannot just look at that as a composition. Also, we are always considering what we know about the subject. E.g. if we have a photograph of a man standing in water, if the photograph ends just below the place that his legs go into the water, we will have the impression that his legs are cut off, and that there is something wrong about the photograph. Finally, facial expression is immensely important for the perceived esthetics of a photograph.
I did some experimenting -- some of the truly great photographs of our times got rather lousy scores (e.g. Dorothea Lange's famous photograph, but also some color photographs as well), while at the same time rather random shots I did of my sons got even five out of five stars. Well. Maybe it will still be useful to someone to filter out the worse photographs.
j.
Apparently, there is a skewed (high) rating for: white or black frame around the picture and black and white photographs esp. portraits.
j.
Something is wrong with this algorithm, this picture scores only 73.4 http://jailbait.4chan.nu/1158384480788.jpg [4chan.nu]
Isn't this exactly the same as the matrix metering introduced in SLR cameras in the eighties? Just instead of calculating recommended exposure you get an estimation.
The principle should be similar - get several thousands of really good pictures that anybody likes. The more, the better. Run analysis for patterns and store the results in a database. And when you need to evaluate a picture, just search for available patterns.
Being a recent Penn State grad, I am somewhat familiar with the application. One thing they didn't state is that this program has the ability to learn. You can teach the program so that it will change its rating system. The drawbrak... you have to take the time to teach this program which is never fun. And I'm far to lazy so I will never do it. It could be a useful application in some cameras, for the terms for red eye, lighting and clarity.
Just because you are wrong and I called you out on it doesn't mean I am a Troll.
This picture gets 95.1%
This, completely different picture, gets 9.8%.
While this one gets 7.3%.
Note that the one that actually represents the photographed object the best got horrible grades, but the blurred, oversaturated and cropped version got nearly perfect score.
Mit der Dummheit kämpfen Götter selbst vergebens
From what I can see, it's just a sunset detector. http://www.flickr.com/photos/snorfalorpagus/3171129414/ scores 50.5. http://www.flickr.com/photos/snorfalorpagus/3285583334/ scores 50. http://www.flickr.com/photos/snorfalorpagus/3399530552/ scores 19.1.
According to him, this picture sucks.
put this software in a feedback loop, and you can actually make a system that *improves* the quality of a photo :-)
So I follow the link and think, hey this is pretty cool. I grab some screen shots of my apps and run them through. Unsurprisingly, some old VB6 crap I'm still maintaining was scoring in the 5-10% range. The newer Web and Silverlight apps I've been working on are all over from 30%-70%. I'm thinking this software is pretty cool and we could use it to get rapid feedback on different layouts and styles.
So I send the link to one of my co-workers. He brings it up and posts a screen shot of his web site. We start talking about how we could use it and how it works. And we wind up with a little impromptu meeting at his cubicle. 5 people huddled around his desk checking out the rating system.
And then we hit the home page, were recent highly rated photo thumbnails are shown. And what do we see?
Some lady, buck naked, leaning on her shoulder blades, twisted up like a pretzel shooting an anal douche fountain a few feet into the air.
And that is why you never trust a machine to rate user submitted images.
-Rick
"Most people in the U.S. wouldn't know they live in a tyrannical state if it walked up and grabbed their junk." - MyFirs
I wonder what scores it gives to porn?
We are the 198 proof..
I, for one, do not welcome our new aesthetically aware computer overlords. I get enough of that from the chicks at my uni.
You know, there is a difference between trolling and pointing out the flaws in your reasoning. Just saying.
and this isn't a computer research project at all but rather a sly psychological study trying to gather a collection of images which real humans are aesthetically interested in. ..perhaps correlated by IP / physical region or perhaps correlated to before and after being posted on slashdot.
try uploading this image (it's clean) several times. it generally gets a 98.9, but sometimes gets a 5.6. after mirroring the image it generally gets a slightly reduced 98.4 but occasionally gets a 35.4.
Finally! Now I can look at pictures that other people think are amazing. At last, my personal preference for photography can fall in line with the consensus of strangers on the Internet. I'm so happy to have found this Acquine thing! Now I'll like all the same stuff everyone else likes, like a normal person. After all, having individual taste is treachery. Fall in line with the group, everyone!
Apparently that's all that this measures really, because I tried some moderately popular photographs I'd taken and put on deviantart and they got rated very poorly. So I tried an extremely popular one from my favorites, and that also got rated very poorly. You could call it an interesting experiment, but first it would have to show any sign of working.
I uploaded a picture of my wife; the computer's response was "I'd hit that!"
Are we sure they are not using a Mechanical Turk?
I've abandoned my search for truth; now I'm just looking for some useful delusions.
Beta testers noted that images of mares were particularly appealing to the software.
https://www.eff.org/https-everywhere
We have a clean winner here:
Princess Leia: 76.5 %
Padme Amidala: 59.3 %
(source of both pics: Wikipedia)
And I haven't tried the famous bikini photo!
1) Aesthetic according to what standard?
2) Art is more than photos. Much art moved away from realism 150 years ago.
Some short thoughts on the topic by a physicist.