US 12,260,633 B2
Method for detecting defects and electronic device
Fu-Yuan Tan, Taoyuan (TW); and Ching-Han Cheng, Taoyuan (TW)
Assigned to Fulian Precision Electronics (Tianjin) Co., LTD., Tianjin (CN)
Filed by Fulian Precision Electronics (Tianjin) Co., LTD., Tianjin (CN)
Filed on May 24, 2022, as Appl. No. 17/752,033.
Claims priority of application No. 202111545294.2 (CN), filed on Dec. 16, 2021.
Prior Publication US 2023/0196756 A1, Jun. 22, 2023
Int. Cl. G06V 10/98 (2022.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06V 10/70 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/993 (2022.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06V 10/82 (2022.01); G06V 10/87 (2022.01)] 15 Claims
OG exemplary drawing
 
1. A defect detection method comprising:
obtaining a first image corresponding to a first area on an object; wherein the first area is where an area on the object determined to be defective after a first detection;
selecting a detection model according to a size of the first image; and
detecting defects on the first image according to the detection model and outputting a detection result;
selecting the detection model according to a proportion of a length of the first image and a width of the first image;
wherein the selecting the detection model according to a proportion of length and width of the first image, further comprises:
selecting a first detection model if the length of the first image is greater than the width of the first image;
selecting a second detection model if the length of the first image is less than the width of the first image.