US Patent Issued to Fortinet on Oct. 28 for "Systems and methods for facial recognition training dataset adaptation with limited user feedback in surveillance systems" (California Inventor)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,455,941, issued on Oct. 28, was assigned to Fortinet Inc. (Sunnyvale, Calif.).

"Systems and methods for facial recognition training dataset adaptation with limited user feedback in surveillance systems" was invented by Xihua Dong (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Various embodiments provide systems and methods for updating a training dataset so that the generated machine learning model can adapt to both short-term and long-term face variations including, for example, head pose, dressing, lighting conditions, and/or aging."

The patent was filed on May 20, 2021, under Application No. 17/325,943.

*For further information, i...