US Patent Issued to Netskope on May 27 for "Image classification and accelerated classification training using deep learning image fingerprinting models and indexed embeddings" (California Inventors)

ALEXANDRIA, Va., June 17 -- United States Patent no. 12,315,231, issued on May 27, was assigned to Netskope Inc. (Santa Clara, Calif.).

"Image classification and accelerated classification training using deep learning image fingerprinting models and indexed embeddings" was invented by Yihua Liao (Palo Alto, Calif.), Niranjan Koduri (Pleasanton, Calif.), Emanoel Daryoush (San Jose, Calif.), Jason B. Bryslawskyj (San Diego), Yi Zhang (Santa Clara, Calif.), Ari Azarafrooz (Rancho Santa Margarita, Calif.) and Wayne Xin (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Image fingerprints (embeddings) are generated by an image fingerprinting model and indexed with an approximate nearest neighbors...