How Computer Vision Algorithms Cope With Detecting Human Figures In Art 22
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.
I bet... (Score:1)
this is all an excuse by shut-in professors to watch kinky porn at work.
Where do you get the answer key? (Score:4, Insightful)
Re: (Score:2)
From the beholders - they asked 18 volunteers to identify where the "person" was in each image, and tested how well each algorithm identified the same section of the picture.
Recognize deformable body parts (Score:2)
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 [youtube.com] :-)
Re: (Score:1)
It's called the Jeffrey Dahmer Algorithm.
Re: (Score:2)
It's called the Jeffrey Dahmer Algorithm.
This is incredibly tasteless. And funny.
Re: (Score:1)
Pun intended?
Still can't find Waldo... (Score:4, Funny)
Still can't find Waldo...
Moon face? (Score:2)
Did they try their algorithms on that "moon face"? Does it see the same thing humans see, i.e. a face?
Re: (Score:1)
Would like to see the fruits of this algorithm (Score:2)
... when performed on Archimboldo's works; no body parts there, though human figures plenty.
Already solved (Score:2)
Spammers already solved this problem ages ago when trying to circumvent CAPTCHAs.