Boston researchers Northeastern University have built a device using new artificial intelligence techniques capable of recognizing “millions of colors”, opening the door to a new world of industrial machine vision applications.
A-Eye is able to analyze and process colors much more accurately than existing machines, according to an article detailing research published in materials today. The researchers say the new device represents “a massive step” in computer vision and has broad applications for a range of technologies.
The ability of machines to detect or “see” color is an increasingly important feature in enterprise computing, according to Swastika Karassociate professor of physics at Northeastern who co-authored the research with support from a physics doctoral student Davud Hejazi. “In the world of automation, shapes and colors are the most commonly used elements by which a machine can recognize objects,” he explains.
Researchers have engineered a two-dimensional material with special quantum properties that allows it to process a rich diversity of colors with “very high precision” for the first time. A-Eye archives this using machine learning algorithms developed by a team of AI researchers led by Sarah Ostadabbas, assistant professor of electrical and computer engineering at Northeastern. The project is the result of a collaboration between Northeastern Quantum Materials and Augmented Cognition Laboratories.
“It’s about what happens to light when it passes through quantum matter,” Kar explains. “When we grow these materials on a certain surface and then let the light through, what comes out of that other end, when it hits a sensor, is an electrical signal that [Ostadabbas’s] group can treat as data.
Automotive, agriculture and telecommunications will benefit from machine vision
There are many industrial applications of machine vision for research, which would include autonomous vehicles, agricultural sorting and remote satellite imagery, Kar says.
“Color is used as one of the main components to recognize ‘good’ from ‘bad’, ‘good’ from ‘not good’, so there’s a huge implication here for a variety of industrial uses,” explains he.
Instead of using filters, Kar and his team used “transmissive windows” made of a single two-dimensional material, which represents a very different way of approaching the problem using machine vision.
When light passes through these windows, the machine treats the color as data, Ostadabbas explains. Machine learning models then look for patterns to better identify matching colors analyzed by the device.
“Instead of breaking it down into its main red, green and blue components, when colored light appears on, for example, a detector, instead of just looking for those components, we use the entire spectral information,” says Kar . “And on top of that, we use certain techniques to modify and encode them, and store them in different ways. So it provides us with a set of numbers that help us recognize the original color in a much more unique way than the conventional method. »
Comments are closed.