US 12,106,485 B2
Edge-guided human eye image analyzing method
Feng Lu, Beijing (CN); Yuxin Zhao, Beijing (CN); Zhimin Wang, Beijing (CN); and Qinping Zhao, Beijing (CN)
Assigned to Beihang University, Beijing (CN)
Filed by Beihang University, Beijing (CN)
Filed on Apr. 26, 2022, as Appl. No. 17/729,839.
Claims priority of application No. 202111121554.3 (CN), filed on Sep. 24, 2021.
Prior Publication US 2022/0254031 A1, Aug. 11, 2022
Int. Cl. G06T 7/12 (2017.01); G06V 40/18 (2022.01)
CPC G06T 7/12 (2017.01) [G06V 40/193 (2022.01); G06T 2207/20084 (2013.01); G06T 2207/30201 (2013.01)] 10 Claims
OG exemplary drawing
 
1. An edge-guided human eye image analyzing method, comprising:
using a camera to collect a human eye image as an image to be detected, wherein the image to be detected comprises at least one of the following: a pupil area, an iris area, an upper eyelid area, and a lower eyelid area;
inputting the image to be detected to a pre-trained contour generation network to obtain a human eye detection contour map;
inputting the image to be detected and the human eye detection contour map to a pre-trained edge-guided analyzing network, to obtain a semantic segmentation detection map and an initial human eye image detection fitting parameter;
based on the semantic segmentation detection map, performing an iterative search on the initial human eye image detection fitting parameter to determine a target human eye image detection fitting parameter;
sending the semantic segmentation detection map and the target human eye image detection fitting parameter as image analyzing results to a display terminal for display.