US 11,790,494 B2
Facial verification method and apparatus based on three-dimensional (3D) image
Seungju Han, Seoul (KR); Minsu Ko, Suwon-si (KR); Jaejoon Han, Seoul (KR); and Chang Kyu Choi, Seongnam-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Dec. 2, 2021, as Appl. No. 17/540,307.
Application 17/540,307 is a continuation of application No. 16/426,460, filed on May 30, 2019, granted, now 11,200,405.
Claims priority of application No. 10-2018-0061946 (KR), filed on May 30, 2018.
Prior Publication US 2022/0092295 A1, Mar. 24, 2022
Int. Cl. G06K 9/00 (2022.01); G06T 5/00 (2006.01); G06T 7/73 (2017.01); G06T 5/50 (2006.01); G06V 40/16 (2022.01)
CPC G06T 5/005 (2013.01) [G06T 5/50 (2013.01); G06T 7/73 (2017.01); G06V 40/165 (2022.01); G06V 40/171 (2022.01); G06V 40/172 (2022.01); G06T 2207/10012 (2013.01); G06T 2207/20216 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30201 (2013.01)] 20 Claims
OG exemplary drawing
 
12. An electronic apparatus comprising:
a processor configured to:
obtain a facial image including a 3D face of a user;
determine an occluded region in the facial image by comparing the facial image and a target facial image;
determine a reliability of the facial image based on the occluded region in the facial image; and
verify the user based on the determined reliability of the facial image,
wherein the processor is further configured to:
extract features from the facial image to perform a facial verification using a landmark detection based on a neural network model; and
terminate the verifying using the facial image without extracting features from the facial image based on the reliability of the facial image.