20 March 2016

How Computers and Brains Recognize Images

We do not merely recognize objects, our brain is so good at this task that we can automatically supply the concept of a cup when shown a photo of a curved handle or identify a face from just an ear or nose. Neurobiologists, computer scientists, and robotics engineers are all interested in understanding how such recognition works (in both human and computer vision systems). New research suggests that there is an atomic unit of recognition, a minimum amount of information an image must contain for recognition to occur. In the field of computer vision, for example, the ability to recognize an object in an image has been a challenge for computer and artificial intelligence researchers. Researchers, wanted to know how well current models of computer vision are able to reproduce the capacities of the human brain. To this end they enlisted thousands of participants from Amazon's Mechanical Turk and had them identify series of images. The images came in several formats: Some were successively cut from larger images, revealing less and less of the original. Others had successive reductions in resolution, with accompanying reductions in detail.


When the scientists compared the scores of the human subjects with those of the computer models, they found that humans were much better at identifying partial- or low-resolution images. The comparison suggested that the differences were also qualitative: Almost all the human participants were successful at identifying the objects in the various images, up to a fairly high loss of detail -- after which, nearly everyone stumbled at the exact same point. The division was so sharp; the scientists termed it a phase transition. The researchers suggest that the differences between computer and human capabilities lie in the fact that computer algorithms adopt a bottom-up approach that moves from simple features to complex ones. Human brains, on the other hand, work in "bottom-up" and "top-down" modes simultaneously, by comparing the elements in an image to a sort of model stored in their memory banks. The findings also suggest there may be something elemental in our brains that are tuned to work with a minimal amount, a basic atom of information. That elemental quantity may be crucial to our recognition abilities, and incorporating it into current models could improve their sensitivity.

More information: