illustrative image of an eye with computer powers

UCF researchers develop technology for AI that mimics the human eye

Researchers at the University of Central Florida have developed an artificial intelligence device that mimics the retina of the eye.

The development could lead to advanced AI that can immediately recognize what it sees, such as automatic descriptions of photos taken with a camera or phone. The technology also has applications in self-driving vehicles and robotics.

The device, which is described in a new study in the journal ACS Nanoalso outperforms the eye in the number of wavelengths it can see, from ultraviolet to visible light and beyond to the infrared spectrum.

It is also unique for its ability to integrate three different operations into one. Today’s intelligent imaging technology, such as that used in self-driving vehicles, requires separate detection, memorization and processing of data.

By combining the three steps, the UCF-designed device is many times faster than current technology, the researchers say. The technology is also very small, with hundreds of devices fitting on a one-inch chip.

AI device that mimics the retina of the human eye
The technology is very small, with hundreds of devices that fit on a one-inch chip.

“It will change the way artificial intelligence is realized today,” said lead researcher Tania Roy, an assistant professor at UCF’s Department of Materials Science and Engineering and NanoScience Technology Center† “Nowadays, everything is made up of discrete components and runs on conventional hardware. And here we have the capacity to do in-sensor computing with a single device on one small platform.”

The technology builds on previous work by the research team that developed the brain-like devices that allow AI to work in remote regions and in space

“We had devices that acted like the synapses of the human brain, yet we didn’t give them the image directly,” Roy says. “Now by adding image detection capability to it, we have synapse-like devices that act like ‘smart pixels’ in a camera by detecting, processing and recognizing images simultaneously.”

For self-driving vehicles, the device’s versatility allows for safer driving in a variety of conditions, including at night, says Molla Manjurul Islam ’17MSthe lead author of the study and a doctoral student in UCFs Department of Physics

“If you’re in your autonomous vehicle at night and the car’s imaging system only works on a certain wavelength, say the visible wavelength, it won’t see what’s in front of it,” Islam says. “But in our case, with our device, it can actually see across the state.”

“No device like this has been reported that can operate in the ultraviolet range and the visible wavelength and in the infrared wavelength simultaneously, so this is the most unique selling point for this device,” he says.

Molla Manjurul Islam, the lead author of the study and a doctoral student in the UCF’s Department of Physics, examines the retina-like devices on a chip.

Key to the technology is the engineering of nanoscale surfaces made of molybdenum disulfide and platinum ditelluride to enable multi-wavelength sensing and memory. This work was conducted in close collaboration with YeonWoong Jung, an assistant professor with joint appointments in UCF’s NanoScience Technology Center and Department of Materials Science and Engineering, part of UCF’s College of Engineering and Computer Science

The researchers tested the device’s accuracy by having it sense and recognize a mixed wavelength image — an ultraviolet number “3” and an infrared portion that is the mirror image of the number placed together to form an “8.” .They showed that the technology could distinguish the patterns and identify them as both a “3” in ultraviolet and an “8” in infrared.

“We have an accuracy of 70 to 80%, which means they have a very good chance that they can be realized in hardware,” said study co-author Adithi Krishnaprasad ’18MSa PhD student in UCFs Department of Electrical and Computer Engineering

The researchers say the technology could become available for use within five to 10 years.

Study co-authors also included Durjoy Dev ’21graduated from UCF’s doctoral program in electrical engineering; Ricardo Martinez-Martinez ’19MSa student in UCFs doctoral program in optics and photonics† Victor Okonkwo, a UCF student studying Biomedical Sciences and mechanical engineering† Benjamin Wu with Stony Brook University; Sang Sub Han, a postdoctoral associate in the Jung Research Group at UCF; Tae-Sung Bae and Hee-Suk Chung with the Korea Basic Science Institute; and Jimmy Touma, a research scientist at the US Air Force Research Laboratory.

The work was funded by the US Air Force Research Laboratory through the Air Force Office of Scientific Research, and the US National Science Foundation through the CAREER program.

Roy joined UCF in 2016 and is part of the NanoScience Technology Center with a joint appointment at the Faculties of Materials Science and Engineering, the Faculty of Electrical and Computer Engineering and the Faculty of Physics. Hair National Science Foundation CAREER Prize focuses on the development of devices for artificial intelligence applications. Roy was a postdoctoral researcher at the University of California, Berkeley before joining UCF. She received her PhD in electrical engineering from Vanderbilt University.

Leave a Comment

Your email address will not be published.