By Radhika Chauhan
Scientists can now study brain waves to reconstruct the face of the person you are thinking about. A scientific journal published by neuroscientists at the University of Toronto, Scarborough discusses at length how electroencephalography (EEG) data and certain machine-learning algorithms can help reconstructing an image that shows what, or who, a person is thinking about.
The method
Developed by Dan Nemrodov, the technique first straps the test subjects to an EEG apparatus. The subjects are then showed images of anonymous faces; their brain activity is recorded and is then used to regenerate the images the subject is thinking about by using a series of machine learning algorithms. “When we see something, our brain creates a mental percept, which is essentially a mental impression of that thing. We were able to capture this percept using EEG to get a direct illustration of what’s happening in the brain during this process,” says Nemrodov, a post-doctoral fellow at the University of Toronto.
While it does sound exhilarating, this is also not the first time scientists have tried image reconstruction. Adrian Nestor used functional magnetic resonance imaging (fMRI) to measure brain activity by studying the change in blood flow, which also offered finer details. Why then the need of EEG? Not only is EEG relatively cheaper, but is also practical due to its portability. “fMRI captures activity at the time scale of seconds, but EEG captures activity at the millisecond scale. So we can see with very fine detail how the percept of a face develops in our brain using EEG”, says Nemrodov. The EEG technique does come with its share of problems. Occasional eye blinks and muscle tension may tamper with the collection of clean EEG data as a result of which the process stimuli administration and EEG data collection may have to be repeated again.
Going beyond the limits of current technology
Presently only limited to faces and the presence of stimuli, research is being performed to determine how an image can be reconstructed from memory alone, and how it could be applied to objects other than faces. Nevertheless, the study does prove that EEG has potential not only from a practical and neurotechnological standpoint but that it can provide a range of clinical applications too. “It could provide a means of communication for people who are unable to verbally communicate. Not only could it produce a neural-based reconstruction of what a person is perceiving, but also of what they remember and imagine, of what they want to express,” says Adrian Nestor, co-author of the journal published in eNeuro on EEG image reconstruction. “It could also have forensic uses for law enforcement in gathering eyewitness information on potential suspects rather than relying on verbal descriptions provided to a sketch artist.”
“The fact we can reconstruct what someone experiences visually based on their brain activity opens up a lot of possibilities,” said Nestor. Could this then also serve as a medium for studying dreams, a branch of human psychology still limited to psychoanalytical conclusions? It is a point of no debate that this technique can open the doors to a myriad of possibilities. Since we are looking at reconstructing faces instead of mere shapes and figures, the future implications cannot be ignored. Can one assume that perhaps the act of mind-reading will no longer be limited to fiction after all?
Featured Image Source: Visual Hunt
Stay updated with all the insights.
Navigate news, 1 email day.
Subscribe to Qrius
