Key Highlights
- Researchers designed new software to perform computerized image editing using the electric signals from the human brain.
- The results of this software are presented in a paper published at the CVPR 2022.
One of the possible implications of new research at the University of Copenhagen and the University of Helsinki is that computers could sense the problem of the users and come to the rescue soon.
Tuukka Ruotsalo, Associate Professor, Department of Computer Science, University of Copenhagen, said that they could get the images edited by the computer based on thoughts generated by human subjects. The computer does not have prior information on which features it is supposed to edit or how. Nobody has ever done this before.
The results of this new computerized image editing software are presented in a paper accepted for publication at the CVPR 2022 (Computer Vision and Pattern Recognition).
Human Brain Activity As The Sole Input
In the initial study, 30 participants were equipped with hoods containing EEG electrodes that map electrical brain signals. All of them were given the same 200 facial images to look at. Also, they were given a series of tasks like looking for older people, female faces, blond hair, etc.
The participants did not perform any action and looked briefly at the images at the rate of 0.5 seconds per image. The machine first mapped the given preference and then edited the photos accordingly based on their brain activity. So if the task was to look for older people, the computer would modify the portraits of the younger persons, making them look older. And if the task was to look for given hair color, all images would get that color.
Ph.D. student Keith Davis from the University of Helsinki commented that the computer has no idea of face recognition and would have no knowledge about gender, hair color, or other features. Still, the image editing software only edited the feature in question, leaving other facial features unchanged.
Some may argue that many image editing software can manipulate facial features. That would be missing the point. Keith Davis explains that all the existing software was previously trained with labeled input. So, if you want an app that can make people look older, you feed it thousands of portraits and tell the computer which ones are young and which are old. Here, the sole input was the brain activity of the subjects. It is an entirely new paradigm in artificial intelligence using the human brain directly as an input source.”
Possible Applications of The New Computerized Image Editing Software in Medicine
One possible application of this image editing software could be in medicine. Tuukka Ruotsalo said that doctors already use artificial intelligence in the interpretation of scanning images. However, mistakes do happen.
Another application could be assisting a specific group of disabled people, for example, allowing a paralyzed person to operate their computer.
For more such updates on Latest Software Follow our Blog
