US 11,734,804 B2
Face image processing method and apparatus, electronic device, and storage medium
Mingyang Huang, Beijing (CN); Wanzeng Fu, Beijing (CN); Jianping Shi, Beijing (CN); and Yi Qu, Beijing (CN)
Assigned to BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD., Beijing (CN)
Filed by BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD., Beijing (CN)
Filed on Mar. 16, 2022, as Appl. No. 17/696,223.
Application 17/696,223 is a continuation of application No. 16/729,427, filed on Dec. 29, 2019, granted, now 11,341,768.
Application 16/729,427 is a continuation of application No. PCT/CN2018/117498, filed on Nov. 26, 2018.
Claims priority of application No. 201811141270.9 (CN), filed on Sep. 28, 2018.
Prior Publication US 2022/0207910 A1, Jun. 30, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 40/16 (2022.01); G06T 5/00 (2006.01); G06T 7/90 (2017.01); G06T 5/20 (2006.01); G06V 10/56 (2022.01)
CPC G06T 5/005 (2013.01) [G06T 5/002 (2013.01); G06T 5/20 (2013.01); G06T 7/90 (2017.01); G06V 10/56 (2022.01); G06V 40/162 (2022.01); G06V 40/165 (2022.01); G06V 40/171 (2022.01); G06T 2207/30201 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A face image processing method, comprising:
obtaining face key points and a face deflection angle in a face image;
determining a submalar triangle center in the face image according to the face key points and the face deflection angle;
determining a submalar triangle region in the face image according to the face key points and the submalar triangle center; and
performing color filling on the submalar triangle region,
wherein the performing color filling on the submalar triangle region comprises:
determining a first reference point in the face image;
determining a vector that points from the submalar triangle center to the first reference point as a first reference vector;
determining a second target pixel corresponding to each pixel in the submalar triangle region according to the first reference vector, wherein direction of a vector that points from the second target pixel to its corresponding pixel is the same as that of the first reference vector; and
updating a pixel value of each pixel to a pixel value of the second target pixel corresponding to the pixel.