July 12, 2006
Brain Meets Computer Again
Brain meets computer, the next chapter. A brain-computer-interface technology created by researchers at Columbia University could turn our brains into automatic image-identifying machines that operate faster than human consciousness.
By combining the processing power of the human brain with computer vision, researchers have developed a novel device that will allow people to search through images ten times faster than they could on their own.
Supported by a grant from Darpa, or the Defense Advanced Research Projects Agency, the hope is that this cortically coupled computer vision system, known as C3 Vision, would allow hours of footage to be very quickly processed, so security officers could identify terrorists or other criminals caught on surveillance video much more efficiently. 
According to the lead researcher, Paul Sajda at the Laboratory for Intelligent Imaging and Neural Computing, "Our human visual system is the ultimate visual processor." This system harnesses the brain's well-known ability to recognize an image much faster than the person can identify it.The brain emits a signal as soon as it sees something interesting, and that "aha" signal can be detected by an electroencephalogram, or EEG cap. While users sift through streaming images or video footage, the technology tags the images that elicit a signal, and ranks them in order of the strength of the neural signatures. Afterwards, the user can examine only the information that their brains identified as important, instead of wading through thousands of images.
No existing computer vision systems connect with the human brain, and computers on their own don't do well at identifying unusual events or specific targets.The new system's advantage lies in combining the strengths of traditional computer vision with human cortical vision.
For example, when a computer searches for vehicles, it will identify and discard parts of the image that contain water. The human user, who is more likely to easily spot oddities, can then look only at the parts of the image that matter. This could allow time-sensitive searches to be performed in real time.
Laboratory for Intelligent Imaging and Neural Computing
Posted by rsk at July 12, 2006 10:43 PM