US Patent Issued to SEIKO EPSON on March 3 for "Method for generating training data used to learn machine learning model, system, and non-transitory computer-readable storage medium storing computer program" (Japanese Inventor)

ALEXANDRIA, Va., March 3 -- United States Patent no. 12,567,241, issued on March 3, was assigned to SEIKO EPSON Corp. (Japan).

"Method for generating training data used to learn machine learning model, system, and non-transitory computer-readable storage medium storing computer program" was invented by Hiromitsu Mizukami (Matsumoto, Japan).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes: (a) executing prior learning of the machine learning model, using simulation data of an object; (b) capturing a first image of the object from a first direction of image capture; (c) recognizing a first position and attitude of the object from the first image, using the machine learning model already learned ...