AI recreates hyper realistic human faces by reading people’s minds

I’ve seen a lot of sci-fi like innovations now that have let researchers translate human brainwave patterns  and then use Artificial Intelligence (AI) to reconstruct them live into sentences, videos, and images - AKA mind reading. And, while all of them have been impressive, I’ve been waiting for the day when the outputs would be high quality. Now, thanks to researchers at Radboud University in the Netherlands, and an expensive fancy machine it seems we’re finally “getting there.”

This week the researchers developing “mind reading” technology that can translate a person’s brainwaves into photographic images announced a new break though.

In an article published in Nature they revealed the results from an experiment where they showed photos of faces to two volunteers inside a powerful brain-reading Functional Magnetic Resonance Imaging (fMRI) scanner.

Inside the Mind Reading machine

An fMRI scanner is a type of non-invasive brain imaging technology that detects brain activity by measuring the minute changes in the brains blood flow as it thinks and does things.

As the volunteers looked at the images of faces, the fMRI scanned the activity of neurons in the areas of their brain responsible for vision. The researchers then fed this information into a computer’s AI algorithm which could build an accurate image based on the information from the fMRI scan.

As the results of the experiment show, the fMRI/AI system was able to almost identically reconstruct the original images that the volunteers were shown and not only is that a world first but it’s damn impressive.

AI researcher and a cognitive neuroscientist, Thirza Dado, who led the study, believes that these highly impressive results demonstrate the potential for fMRI/AI systems to effectively read minds in future, according to the Mail Online.

“I believe we can train the algorithm not only to picture accurately a face you’re looking at, but also any face you imagine vividly, such as your mother’s,” explains Dado.

“By developing this technology, it would be fascinating to decode and recreate subjective experiences, perhaps even your dreams,” Dado says. “Such technological knowledge could also be incorporated into clinical applications such as communicating with patients who are locked within deep comas.”

Dado’s work is focused on using the technology to help restore vision in people who, through disease or accident, have become blind, reports the Mail Online.

“We are already developing brain-implant cameras that will stimulate people’s brains so they can see again,” Dado says.

To “train” the AI system, the volunteers had previously been shown a series of other faces while their brains were being scanned.

According to the experiment, the key is that the photographic pictures they saw were not of real people, but essentially a paint-by-numbers picture created by a computer where each tiny dot of light or darkness is given a unique computer program code.

The fMRI scan was able to detect how the volunteers’ neurons responded to these “training” images. The artificial intelligence system then translated each volunteer’s neuron reaction back into computer code to recreate the photographic portrait.

In the test, neither the volunteers nor the AI system had ever seen the faces that were decoded and recreated so accurately.