28 September 2007

Computer pacalit de iluziile optice

Cele doua nuante de gri din imaginea de mai sus (iluzia lui White) sunt de fapt identice. De ce apare aceasta iluzie? Teoria e ca bebelusii invata prin incercare si eroare cum sa distinga intre o culoare intunecata datorata faptului ca obiectul se afla in umbra si o culoare intunecata in sine. A face distinctia asta e insa destul de greu, si in anumite conditii creierul o da in bara - ca in cazul de mai sus, sau de mai jos:
Until now there has been no way of knowing whether this theory is correct. Beau Lotto and David Corney at University College London, UK, think they have finally done it. They created a program that learns to predict the lightness of an image based on its past experiences – just like a baby. And just like a human, it falls prey to optical illusions. They trained it using 10,000 greyscale images of fallen leaves that animals might face in nature. It had to predict the true shade of the centre pixel of the images, and change its technique depending on whether its answer was right or wrong. The researchers then tested the program on lightness illusions that would fool humans. First, it was shown images of a light object on a darker background, and vice versa. Just like humans, the software predicted the objects to be respectively lighter and darker than they really were. It also exhibited more subtle similarities – overestimating lighter shades more than darker shades. Next, the researchers tried White's Illusion. Again like a human, the program saw areas of grey as darker when placed on a black stripe, and lighter when placed on a white stripe. Previous computer models tried to directly copy the brain's structure. They could fall for either of the two illusions, but unlike a human, not both at once. Inbuilt failings Lotto's programme was instead just designed to judge shades through learning, without being modelled on the brain. He says that suggests our ability to see illusions really is a direct consequence of learning to filter useful information from our environment. "We didn’t evolve to see things accurately, but to see things that would be useful." Lotto points out. That has implications for robot vision. Most creators of machine vision try to copy human vision because it is so well suited to a variety of environments. The new findings suggest that if we want to exploit its advantages, we also have to suffer its failings. It will be impossible to create a perfect, superhuman robot that never makes mistakes. "I think it's a sensible conclusion," says Olaf Sporns, of Indiana University, Bloomington, US. "If you build machine vision systems that perform similarly to humans, you should expect them to be subject to the same illusions." Thomas Serre, a vision expert at the Massachusetts Institute of Technology, Cambridge, US, is impressed with the team's results. "It's a very neat and elegant way of showing that [learning experiences] alone can explain illusions," he says.