RESTON, Va. — May 11, 2022 — Noblis, Inc., a leading provider of science, technology and strategy services to the federal government, today announced the award of U.S. patent 11,275,973 for a method to improve low-quality images to enhance the ability of pre-trained algorithms to classify them.
“Computers have proven to be good learners when it comes to classifying images. But even a strong system can struggle with a poor-quality image,” said Charles Otto, a Noblis research team lead and the method’s inventor. “This technology offers a way for a system to transform those images, with great accuracy, into something it can recognize and classify.”
“This technology could help our clients increase the usability of images from UAVs, where distance and motion blur can compromise the quality of the image,” said Chris Barnett, Noblis chief technology officer. “We’re excited about the advantages this could deliver for our defense and homeland security clients.”
Learn more about Noblis’ capabilities, our internally sponsored research and development program and other patents.
Media Contact Heather Williams firstname.lastname@example.org 571.459.9725