Microsoft Research and University of Washington researchers have devised a scheme to use the human brain as a processor, Technology Review reports.

They used EEG caps to collect the brain activity of people looking at pictures of faces and nonfaces, such as horses, cars, and landscapes. Their brain activity indicated that they subconsciously identified the difference between images of faces and nonfaces. By pooling responses from 8 people, they achieved 98 percent accuracy.

Subconscious brain power could improve automated image search by preclassifying objects to help a computer more accurately identify pictures. One application: quickly sorting snapshots from surveillance videos to find frames with faces and those without.

Curiously, Technology Review also recently reported National Institute of Standards and Technology (NIST) research showing that machine recognition of human individuals has improved tenfold since 2002 and a hundredfold since 1995, and that the best face-recognition algorithms now perform more accurately than most humans can manage.