公开(公告)号：US20220148338A1

公开(公告)日：2022-05-12

申请号：US17586161

申请日：2022-01-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngjun KWAK ,  Byung In YOO ,  Yong-Il LEE ,  Yunhao ZHANG ,  Huxing SUN

IPC: G06V40/40 ,  G06T7/521 ,  G06N3/08 ,  G06V40/16

Abstract: A method with liveness testing may include: acquiring an infrared (IR) image including an object, and a depth image including the object; generating a first preprocessed IR image by performing first edge enhancement preprocessing on the IR image; generating a preprocessed depth image by performing second edge enhancement preprocessing on the depth image; and determining whether the object is a genuine object based on the first preprocessed IR image and the preprocessed depth image.

公开(公告)号：US20250139422A1

公开(公告)日：2025-05-01

申请号：US18919294

申请日：2024-10-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shanshan LV ,  Jonghoon YOON ,  Byung In YOO ,  Changyong SON ,  Sung-Jae CHO ,  Yunhao ZHANG ,  Zhenxin YANG ,  Miao ZHANG

IPC: G06N3/0495

Abstract: A method performed by one or more processors includes: iteratively training layer-specific quantization levels and layer-specific quantization intervals of respective layers of a neural network of original weights by, for each training iteration, adjusting the quantization levels and quantization intervals to reduce a loss that is determined based on the original weights and is determined based on the original weights as quantized according to the quantization levels and quantization intervals at a current iteration of the training.

公开(公告)号：US20230308599A1

公开(公告)日：2023-09-28

申请号：US18188811

申请日：2023-03-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jingu HEO ,  Yunhao ZHANG ,  Yue MA

IPC: H04N5/262 ,  G06T7/00 ,  H04N5/265 ,  H04N5/222

CPC classification number: H04N5/2624 ,  G06T7/97 ,  H04N5/2628 ,  H04N5/265 ,  H04N5/2224 ,  G06T2207/20221

Abstract: A processor-implemented method includes: determining whether a plurality of tile sets of different zoom levels comprises a tile image, based on either one or both of a position of the tile image in a virtual image and a size of the tile image, wherein tile image corresponds to a visible region covered by a preview interface in the virtual image; updating the tile image based on whether the plurality of tile sets comprises the tile image; and generating a preview image corresponding to the tile image by stitching the updated tile image.

公开(公告)号：US20210166045A1

公开(公告)日：2021-06-03

申请号：US16939757

申请日：2020-07-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngjun KWAK ,  Byung In YOO ,  Yong-Il LEE ,  Yunhao ZHANG ,  Huxing SUN

IPC: G06K9/00 ,  G06N3/08 ,  G06T7/521

Abstract: A method with liveness testing may include: acquiring an infrared (IR) image including an object, and a depth image including the object; generating a first preprocessed IR image by performing first edge enhancement preprocessing on the IR image; generating a preprocessed depth image by performing second edge enhancement preprocessing on the depth image; and determining whether the object is a genuine object based on the first preprocessed IR image and the preprocessed depth image.

公开(公告)号：US20230360429A1

公开(公告)日：2023-11-09

申请号：US17807821

申请日：2022-06-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ying MIN ,  Feng ZHU ,  Hanhui LI ,  Huaiwen BAI ,  Yunhao ZHANG ,  Xiaochun YAN ,  Chunmiao JIANG ,  Wenyan ZHENG ,  Yanjun CHEN ,  Jiangbo CHEN ,  Zhijie LV

IPC: G06V40/12

CPC classification number: G06V40/1371 ,  G06V40/1353

Abstract: The present disclosure relates to a fingerprint identification method, device, an electronic apparatus and a storage medium. The fingerprint identification method includes: capturing a fingerprint by a fingerprint sensor, identifying matching pairs of minutiae between the captured fingerprint and a reference fingerprint; calculating a first matching result based on the minutia matching pairs; identifying minutia surrounding features for each minutia of the captured fingerprint in the minutia matching pairs; determining, for each minutia in the minutia matching pairs, whether the minutia surrounding features of the captured fingerprint match with minutia surrounding features of the reference fingerprint; calculating a second matching result based on the determination; and generating an identification result based on the first matching result and the second matching result.