US 12,293,576 B2
Determining type of to-be-classified image based on signal waveform graph
Dongdong Zhang, Beijing (CN)
Assigned to BEIJING ZHENHEALTH TECHNOLOGY CO., LTD., Beijing (CN)
Appl. No. 17/642,568
Filed by BEIJING ZHENHEALTH TECHNOLOGY CO., LTD., Beijing (CN)
PCT Filed Aug. 17, 2021, PCT No. PCT/CN2021/112932
§ 371(c)(1), (2) Date Mar. 11, 2022,
PCT Pub. No. WO2022/198898, PCT Pub. Date Sep. 29, 2022.
Claims priority of application No. 202110322703.6 (CN), filed on Mar. 26, 2021.
Prior Publication US 2024/0046632 A1, Feb. 8, 2024
Int. Cl. G06V 10/86 (2022.01); G06V 10/22 (2022.01); G06V 10/26 (2022.01); G06V 10/30 (2022.01); G06V 10/34 (2022.01); G06V 10/764 (2022.01)
CPC G06V 10/86 (2022.01) [G06V 10/225 (2022.01); G06V 10/267 (2022.01); G06V 10/30 (2022.01); G06V 10/34 (2022.01); G06V 10/764 (2022.01); G06V 2201/03 (2022.01)] 16 Claims
OG exemplary drawing
 
1. An image classification method, comprising:
inputting a to-be-classified image dataset, wherein the image dataset comprises to-be-classified images; and
performing, for each to-be-classified image of the to-be-classified images, operations comprising:
cropping the to-be-classified image with a center of the to-be-classified image as a reference center point to obtain an image having a preset size and comprising a specific region as a standard image;
selecting a pixel array of any single channel in the standard image and drawing a signal waveform graph based on the pixel array; and
determining a type of the to-be-classified image based on the signal waveform graph.