US Patent Issued to Dalian Minzu University on Dec. 16 for "Collaborative active learning classification method for hyperspectral images based on capsule networks" (Chinese Inventors)

ALEXANDRIA, Va., Dec. 16 -- United States Patent no. 12,499,661, issued on Dec. 16, was assigned to Dalian Minzu University (Dalian, China).

"Collaborative active learning classification method for hyperspectral images based on capsule networks" was invented by Liguo Wang (Dalian, China), Heng Wang (Dalian, China), Danfeng Liu (Dalian, China), Ying Xiao (Dalian, China) and Haitao Liu (Dalian, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "A collaborative active learning classification method for hyperspectral images based on capsule networks is provided in the application, the method trains base classifiers CapsViT and CapsGLOM using an initial training set; calculates BvSB values of candidate samples ...