US 12,340,515 B2
Image edge detection method and image edge detection device
Yu Liang, Shanghai (CN)
Assigned to SIGMASTAR TECHNOLOGY LTD, Fujian (CN)
Filed by SigmaStar Technology Ltd., Fuijan (CN)
Filed on Aug. 31, 2022, as Appl. No. 17/899,686.
Claims priority of application No. 202210102432.8 (CN), filed on Jan. 27, 2022.
Prior Publication US 2023/0237668 A1, Jul. 27, 2023
Int. Cl. G06T 7/13 (2017.01); G06T 5/73 (2024.01)
CPC G06T 7/13 (2017.01) [G06T 5/73 (2024.01); G06T 2207/20076 (2013.01)] 13 Claims
OG exemplary drawing
 
1. An image edge detection method, for processing an image comprising a plurality of pixels, the method comprising:
performing a convolution operation on the image by a gradient operator in a first direction and a gradient operator in a second direction, respectively, to obtain a first-direction gradient data and a second-direction gradient data, wherein the first direction is perpendicular to the second direction;
performing a gradient statistical calculation within a neighboring area of a target pixel of the image according to the first-direction gradient data and the second-direction gradient data and accordingly obtaining a gradient statistic; and
determining an edge significance (Je) corresponding to the target pixel according to the gradient statistic,
wherein the edge significance is determined according to a covariance matrix of the gradient statistic, and
wherein the edge significance of the target pixel increases as a difference between an eigenvalue in a main direction of the covariance matrix and an eigenvalue in a secondary direction of the covariance matrix gets larger according to:

OG Complex Work Unit Math