Slashdot Mirror
How Computer Vision Algorithms Cope With Detecting Human Figures In Art
KentuckyFC writes The human visual system has evolved to recognize people in almost any pose under a vast range of lighting conditions. But abstract art pushes this ability to its limits by distorting the human form. In particular, Cubism seeks to represent three-dimensional objects on a two-dimensional plane by juxtaposing snapshots from different angles. The result is that a Cubist picture contains many 'fragments of perception' of the same object. That's why it is often hard for people to recognize the human figures that these pictures contain. Now a group of computer scientists have tested how computer vision algorithms fare at the task of spotting human figures in Cubist art. They compared a variety of different algorithms against humans in trying to spot human figures in 218 Cubist paintings by Picasso. Humans easily outperform all the algorithms at this task. But some algorithms were much better than others. The most successful were based on so-called "deformable parts models" that recognize human figures by looking for body parts rather than the entire form. Interestingly, the team says this backs up various studies by neuroscientists suggesting that the human brain works in a similar way.
this is all an excuse by shut-in professors to watch kinky porn at work.
Table-ized A.I.
In some cases, the "detection" of an object in Art (or meaning in literature) is in the eye of the beholder, unless the artist tells you that is what they meant.
This issue is a bit more complicated than you think.
The most successful were based on so-called "deformable parts models" that recognize human figures by looking for body parts rather than the entire form.
Cue CSI and all those other shows ... and give me a minute to whip up a visual basic interface for it so we can track down the killer :-)
"Transparent" is a shit show that trades on every stereotype going. A man in drag is NOT a transsexual.
Still can't find Waldo...
Did they try their algorithms on that "moon face"? Does it see the same thing humans see, i.e. a face?
Get free satoshi (Bitcoin) and Dogecoins
'Cubism' is yet another form of Jewish degenerate art.
So Braque and Picasso were Jewish. Who knew?
mmm...there doesn't seem to be any mention of Braque, Picasso, or Cubism on that page. In fact, the word "Cubism" doesn't appear anywhere on darkmoon.me - although there is this interesting tidbit:
“It is no measure of mental health to be well adjusted to a profoundly sick society.”
— Krishnamurti
So I guess getting called an idiot and cretin is a complement nowadays...thanks!
... when performed on Archimboldo's works; no body parts there, though human figures plenty.
Wow, I guess that told me then...
It sure did. How does it feel to have your ignorance laid bare for all to see by a mere two sentence reply? What do you think about the possibility that those sentences were written by a Jew? I mean, c'mon..."Who knew?"...you can almost hear it being said with a NY Jewish accent. U mad now bro?
Spammers already solved this problem ages ago when trying to circumvent CAPTCHAs.
If Pandora's box is destined to be opened, *I* want to be the one to open it.
consensus != truth
"...detection of an object in Art (or meaning in literature) is in the eye of the behold..."
Detection of a object is different from interpretation of meaning. The former is a vision science task, while the later is a social, aesthetic task. Of course, they are linked, but usually people might agree more on what is seen, while agreeing less on what it means.
It would be interesting to know the standard deviation in human error as the images become more abstract. In other words, by how much do humans differ in identifying people in abstract paintings.