US 12,236,565 B2
Method and apparatus for classifying image of displaying base plate
Quanguo Zhou, Beijing (CN); Kaiqin Xu, Beijing (CN); Jiahong Zou, Beijing (CN); Guolin Zhang, Beijing (CN); Xun Huang, Beijing (CN); Qing Zhang, Beijing (CN); Zhidong Wang, Beijing (CN); Lijia Zhou, Beijing (CN); Hongxiang Shen, Beijing (CN); Jiuyang Cheng, Beijing (CN); and Hao Tang, Beijing (CN)
Assigned to BOE Technology Group Co., Ltd., Beijing (CN)
Filed by BOE Technology Group Co., Ltd., Beijing (CN)
Filed on Sep. 15, 2021, as Appl. No. 17/476,321.
Claims priority of application No. 202110129183.7 (CN), filed on Jan. 29, 2021.
Prior Publication US 2022/0245782 A1, Aug. 4, 2022
Int. Cl. G06T 7/00 (2017.01); G06F 18/2413 (2023.01); G06N 3/08 (2023.01); G06T 5/50 (2006.01); G06T 7/55 (2017.01); G06V 10/44 (2022.01)
CPC G06T 7/0002 (2013.01) [G06F 18/2413 (2023.01); G06N 3/08 (2013.01); G06T 5/50 (2013.01); G06T 7/55 (2017.01); G06V 10/443 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method for classifying an image of a displaying base plate, wherein the method comprises:
acquiring an image to be checked;
from a first predetermined-type set, determining a type of the image to be checked, wherein the first predetermined-type set comprises: a first image type, a second image type and a third image type, wherein an image of the first image type is a no-defect image, an image of the second image type is a blurred image, and an image of the third image type is a defect image; and
on a condition that the type of the image to be checked is the third image type, by using a first convolutional neural network, determining defect data of the image to be checked, wherein the defect image refers to an image of a displaying base plate having a defect, and the defect data contains a defect type of the displaying base plate in the image to be checked;
wherein the step of, by using a first convolutional neural network, determining the defect data of the image to be checked comprises:
by using the first convolutional neural network, on a condition that the defect type of the image to be checked is in a second predetermined-type set, determining the defect type of the image to be checked from the second predetermined-type set, wherein the second predetermined-type set comprises at least one defect type; and
on a condition that the defect type of the image to be checked is not in the second predetermined-type set, outputting the image to be checked, and receiving a first newly created defect type that is inputted by a user.