The study was conducted by a team of neuroscientists at the University of Toronto Scarborough. Participants looked at images of faces on a computer screen while wearing electroencephalography (EEG) equipment. The researchers then used machine learning algorithms to process the recorded brainwaves. The system then immediately digitally reconstructed the face.
“When we see something, our brain creates a mental percept, which is essentially a mental impression of that thing,” Dan Nemrodov, co-author of the study, told New Atlas. “We were able to capture this percept using EEG to get a direct illustration of what's happening in the brain during this process.”
Going forward, the team hopes to be able to recreate other objects besides just faces, and to increase the amount of time between when someone saw something and when it can be recreated based on the scan. They envision a number of real-world applications for the technology, including assisting law enforcement and providing another means of communication for people who have trouble or are unable to communicate verbally.
The journal eNeuro published the results of team’s research.