US 11,682,232 B2
Device and method with image matching
Sungun Park, Suwon-si (KR); Jihye Kim, Anyang-si (KR); Jaejoon Han, Seoul (KR); Minsu Ko, Suwon-si (KR); Seungju Han, Seoul (KR); Jinwoo Son, Seoul (KR); and Changyong Son, Anyang-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Oct. 1, 2018, as Appl. No. 16/148,129.
Claims priority of application No. 10-2018-0017303 (KR), filed on Feb. 12, 2018.
Prior Publication US 2019/0251237 A1, Aug. 15, 2019
Int. Cl. G06F 21/00 (2013.01); G06V 40/16 (2022.01); G06F 21/32 (2013.01); G06T 7/73 (2017.01); G06F 16/583 (2019.01); G06V 40/40 (2022.01); G06F 18/22 (2023.01); H04N 23/90 (2023.01); G06V 10/75 (2022.01)
CPC G06V 40/172 (2022.01) [G06F 16/5838 (2019.01); G06F 18/22 (2023.01); G06F 21/32 (2013.01); G06T 7/74 (2017.01); G06V 40/45 (2022.01); H04N 23/90 (2023.01); G06T 2207/10024 (2013.01); G06T 2207/10048 (2013.01); G06T 2207/20024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06V 10/759 (2022.01); G06V 40/165 (2022.01); G06V 40/171 (2022.01)] 23 Claims
OG exemplary drawing
 
1. A processor-implemented image matching method, comprising:
photographing, by a first image sensor, an object to acquire a first image;
photographing, by a second image sensor, the object to acquire a second image;
determining a landmark point of the first image based on a neural network model stored in a memory;
extracting, from the first image of the object, a landmark patch including the landmark point of the object;
extracting, from the second image of the object, a target patch corresponding to the landmark patch, wherein a size of the target patch is greater than a size of the landmark patch;
determining a target point in the second image corresponding to the landmark point based on a matching between the landmark patch extracted from the first image and the target patch extracted from the second image;
recognizing the object, in the second image, based on the target point; and
authenticating a user based on the recognized object,
wherein the landmark point comprises both ends of an eye of the user.