JUL 10, 2019 11:35 AM PDT

The Vision of Artificial Vision

WRITTEN BY: Nouran Amin

Researchers seeking to upgrade modern day smartphones have devised a way to create “smart” glass—a method capable of image recognition free from sensors, circuits, or power sources. "We're using optics to condense the normal setup of cameras, sensors and deep neural networks into a single piece of thin glass," says Zongfu Yu, an electrical and computer engineering professor at UW-Madison. "This is completely different from the typical route to machine vision.”

University of Wisconsin: From left to right, Zongfu Yu, Ang Chen and Efram Khoram developed the concept for a “smart” piece of glass that recognizes images without any external power or circuits. PHOTO BY SAM MILLION WEAVER.

"The true power of this technology lies in its ability to handle much more complex classification tasks instantly without any energy consumption," says Ming Yuan, a collaborator on the research and professor of statistics at Columbia University. "These tasks are the key to create artificial intelligence: to teach driverless cars to recognize a traffic signal, to enable voice control in consumer devices, among numerous other examples."

The idea behind smart glass consists of moving beyond artificial intelligence in inert objects. “We're accustomed to digital computing, but this has broadened our view," says Yu. "The wave dynamics of light propagation provide a new way to perform analog artificial neural computing."

The new proof of concept method makes glass pieces from identified handwritten numbers where light emanating from an image of a number will enter at one end of the glass and then focuses to one of nine specific spots. "We're accustomed to digital computing, but this has broadened our view," says Yu. "The wave dynamics of light propagation provide a new way to perform analog artificial neural computing"

University of Wisconsin: Light passing through “smart” glass is bent in a particular pattern depending on the scene, image or (in this case) written number facing the glass. If the light matches an expected pattern, the glass “recognizes” what it sees. IMAGE COURTESY ZONGFU YU

"We could potentially use the glass as a biometric lock, tuned to recognize only one person's face" says Yu. "Once built, it would last forever without needing power or internet, meaning it could keep something safe for you even after thousands of years."

Findings of the study were published in the journal Photonics Research and describe the design of the glass similar to the machine learning process. "The fact that we were able to get this complex behavior with such a simple structure was really something," says Erfan Khoram, a graduate student in Yu's lab.

Watch the video below to learn more:

"We're always thinking about how we provide vision for machines in the future, and imagining application specific, mission-driven technologies." says Yu. "This changes almost everything about how we design machine vision."

Source: University of Wisconsin

About the Author
BS/MS
Nouran is a scientist, educator, and life-long learner with a passion for making science more communicable. When not busy in the lab isolating blood macrophages, she enjoys writing on various STEM topics.
You May Also Like
OCT 24, 2022
Neuroscience
Frankenworld: Should We Be Afraid of Playing God or Failing To Love Our Monsters?
OCT 24, 2022
Frankenworld: Should We Be Afraid of Playing God or Failing To Love Our Monsters?
Lawyer Henry T. Greely analyzes the relevance of Mary Shelley's classic, "Frankenstein," in light of today's bioscience
OCT 14, 2022
Technology
Charging an Electric Vehicle in Just 10 Minutes
OCT 14, 2022
Charging an Electric Vehicle in Just 10 Minutes
Electric vehicles are common and increasingly popular alternative to vehicles powered by traditional combustion engines. ...
OCT 18, 2022
Earth & The Environment
Snatching CO2 From the Air
OCT 18, 2022
Snatching CO2 From the Air
In a recent study published in Nanoscale, a team of researchers led by the University of Pittsburgh have designed new ma ...
NOV 03, 2022
Space & Astronomy
Martian Core Identified Through Planetary Scan
NOV 03, 2022
Martian Core Identified Through Planetary Scan
In a recent study published in Nature Astronomy, a pair of researchers from The Australian National University (ANU) hav ...
NOV 01, 2022
Technology
Arranging Nanoparticles Without Damaging Surface Material
NOV 01, 2022
Arranging Nanoparticles Without Damaging Surface Material
In a recent study published in Science Advances, a team of researchers from the Massachusetts Institute of Technology ha ...
NOV 03, 2022
Space & Astronomy
JWST Takes Stunning Image of Pillars of Creation
NOV 03, 2022
JWST Takes Stunning Image of Pillars of Creation
The James Webb Space Telescope has taken not just one but two breathtaking images of the Pillars of Creation. Located in ...
Loading Comments...