US Patent Issued on May 26 for "Three-stage modularized convolutional neural network for rapidly classifying concrete cracks" (Chinese Inventors)

ALEXANDRIA, Va., May 26 -- United States Patent no. 12,639,924, issued on May 26.

"Three-stage modularized convolutional neural network for rapidly classifying concrete cracks" was invented by Maosen Cao (Nanjing City, China), Ronghua Fu (Nanjing City, China), Yufeng Zhang (Nanjing City, China), Tongfa Deng (Ganzhou City, China), Shuai Li (Nanjing City, China) and Dragoslav Sumarac (Nanjing City, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "Disclosed is a three-stage modular convolutional neural network (CNN), referred to as Stairnet, for efficient classification of concrete cracks in images. Unlike conventional CNNs that employ repetitive layer structures, Stairnet is organized into three distinct s...