US 12,456,168 B2
Artificial intelligence device and method for generating training data
Yi Hu, Seoul (KR); Sangyun Kim, Seoul (KR); Run Cui, Seoul (KR); Hyunwoo Kim, Seoul (KR); and Jaehong Eom, Seoul (KR)
Assigned to LG ELECTRONICS INC., Seoul (KR)
Appl. No. 17/923,068
Filed by LG ELECTRONICS INC., Seoul (KR)
PCT Filed Oct. 14, 2020, PCT No. PCT/KR2020/013978
§ 371(c)(1), (2) Date Nov. 3, 2022,
PCT Pub. No. WO2022/080517, PCT Pub. Date Apr. 21, 2022.
Prior Publication US 2023/0169634 A1, Jun. 1, 2023
Int. Cl. G06T 5/00 (2024.01); G06T 3/40 (2006.01); G06T 5/50 (2006.01); G06T 5/70 (2024.01); G06T 7/00 (2017.01)
CPC G06T 5/50 (2013.01) [G06T 3/40 (2013.01); G06T 5/70 (2024.01); G06T 7/0004 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20092 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30108 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A product inspection apparatus comprising:
a camera configured to capture an image of a product to be inspected; and
a processor configured to:
extract defect information from a defect indicated by the captured image of the product,
generate first virtual defect data including at least one of a location, a size and a shape of the defect included in the captured image, based on the extracted defect information,
generate second virtual defect data by synthesizing the first virtual defect data with non-defect data representing the product without the defect and a virtual mask image representing the defect extracted from the first virtual defect data as a binary image, and
generate final virtual defect data by inputting the second virtual defect data to an artificial intelligence generative model.