Mind Reading Machine Reconstructs Images of What You See

A new technique developed by neuroscientists at University of Toronto Scarborough can, for the first time, reconstruct images of what people perceive based on their brain activity gathered by EEG.

The technique developed by Dan Nemrodov, a postdoctoral fellow in Assistant Professor Adrian Nestor’s lab at U of T Scarborough, is able to digitally reconstruct images seen by test subjects based on electroencephalography (EEG) data.

“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.

For the study, test subjects hooked up to EEG equipment were shown images of faces. Their brain activity was recorded and then used to digitally recreate the image in the subject’s mind using a technique based on machine learning algorithms.

It’s not the first time researchers have been able to reconstruct images based on visual stimuli using neuroimaging techniques. The current method was pioneered by Nestor who successfully reconstructed facial images from functional magnetic resonance imaging (fMRI) data in the past, but this is the first time EEG has been used.

And while techniques like fMRI – which measures brain activity by detecting changes in blood flow – can grab finer details of what’s going on in specific areas of the brain, EEG has greater practical potential given that it’s more common, portable, and inexpensive by comparison. EEG also has greater temporal resolution, meaning it can measure with detail how a percept develops in time right down to milliseconds, explains Nemrodov.

“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,” he says. In fact, the researchers were able to estimate that it takes our brain about 170 milliseconds (0.17 seconds) to form a good representation of a face we see.