公开(公告)号：US11747442B2

公开(公告)日：2023-09-05

申请号：US17019672

申请日：2020-09-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Insoo Kim ,  Seungju Han ,  Jaejoon Han

IPC: G01S7/41 ,  G06F21/44

CPC classification number: G01S7/412 ,  G06F21/44

Abstract: A processor-implemented radar data recognition method includes: generating a plurality of pieces of input data, with respectively different dimension configurations, based on radar data of an object; and outputting a recognition result of the object based on the generated plurality of pieces of input data using a recognition model.

公开(公告)号：US11682232B2

公开(公告)日：2023-06-20

申请号：US16148129

申请日：2018-10-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sungun Park ,  Jihye Kim ,  Jaejoon Han ,  Minsu Ko ,  Seungju Han ,  Jinwoo Son ,  Changyong Son

IPC: G06F21/00 ,  G06V40/16 ,  G06F21/32 ,  G06T7/73 ,  G06F16/583 ,  G06V40/40 ,  G06F18/22 ,  H04N23/90 ,  G06V10/75

CPC classification number: G06V40/172 ,  G06F16/5838 ,  G06F18/22 ,  G06F21/32 ,  G06T7/74 ,  G06V40/45 ,  H04N23/90 ,  G06T2207/10024 ,  G06T2207/10048 ,  G06T2207/20024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V10/759 ,  G06V40/165 ,  G06V40/171

Abstract: An image matching method includes extracting, from a first image of an object, a landmark patch including a landmark point of the object; extracting, from a second image of the object, a target patch corresponding to the landmark patch; and determining a target point in the second image corresponding to the landmark point based on a matching between the landmark patch and the target patch.

公开(公告)号：US11586886B2

公开(公告)日：2023-02-21

申请号：US16542803

申请日：2019-08-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jinwoo Son ,  Changyong Son ,  Seohyung Lee ,  Sangil Jung ,  Chang Kyu Choi ,  Jaejoon Han

IPC: G06N3/063 ,  G06F17/15 ,  G06F9/38

Abstract: A processor-implemented neural network processing method includes: obtaining a kernel bit-serial block corresponding to first data of a weight kernel of a layer in a neural network; generating a feature map bit-serial block based on second data of one or more input feature maps of the layer; and generating at least a portion of an output feature map by performing a convolution operation of the layer using a bitwise operation between the kernel bit-serial block and the feature map bit-serial block.

公开(公告)号：US11544497B2

公开(公告)日：2023-01-03

申请号：US17101552

申请日：2020-11-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Byungin Yoo ,  Youngjun Kwak ,  Jungbae Kim ,  Seon Min Rhee ,  Seungju Han ,  Jaejoon Han ,  Wonjun Hwang

IPC: G06K9/62 ,  G06V10/44 ,  G06V40/16 ,  G06V40/12 ,  G06N3/08 ,  H04L9/40

Abstract: A method and an apparatus for recognizing an object are disclosed. The apparatus may extract a plurality of features from an input image using a single recognition model and recognize an object in the input image based on the extracted features. The single recognition model may include at least one compression layer configured to compress input information and at least one decompression layer configured to decompress the compressed information to determine the features.

公开(公告)号：US11508146B2

公开(公告)日：2022-11-22

申请号：US16991454

申请日：2020-08-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jinwoo Son ,  Changyong Son ,  Chang Kyu Choi ,  Jaejoon Han

IPC: G06V10/94 ,  G06N3/04 ,  G06N3/063 ,  G06K9/62 ,  G06N3/08

Abstract: A convolutional neural network (CNN) processing method and apparatus. The apparatus may select, based on at least one of a characteristic of at least one kernel of a convolution layer or a characteristic of an input of the convolution layer, one operation mode from a first operation mode reusing a kernel, of the at least one kernel, and a second operation mode reusing the input, and perform a convolution operation based on the selected operation mode.

公开(公告)号：US11455384B2

公开(公告)日：2022-09-27

申请号：US17083618

申请日：2020-10-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minsu Ko ,  Seungju Han ,  Jaejoon Han ,  Deoksang Kim ,  Chang Kyu Choi

IPC: G06F21/32 ,  G06F16/583

Abstract: A method and apparatus with an adaptively updated enrollment database (DB) are provided. A method with an adaptively updated enrollment database (DB) includes extracting an input feature vector from an input image, determining whether the input feature vector is included in a changeable enrollment range, with the changeable enrollment range being determined based on a threshold distance from each of plural enrolled feature vectors in the enrollment DB, and with the enrolled feature vectors corresponding to enrolled images, determining whether to enroll the input feature vector in the enrollment DB in response to the input feature vector being determined as being included in the changeable enrollment range, and in response to a result of the determining of whether to enroll the input feature vector being to enroll the input feature vector, selectively enrolling the input feature vector in the enrollment DB.

公开(公告)号：US11348575B2

公开(公告)日：2022-05-31

申请号：US16898634

申请日：2020-06-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sung-Jae Cho ,  Kyuhong Kim ,  Jaejoon Han

IPC: G10L15/20 ,  G10L15/06

Abstract: A speaker recognition method and apparatus receives a first voice signal of a speaker, generates a second voice signal by enhancing the first voice signal through speech enhancement, generates a multi-channel voice signal by associating the first voice signal with the second voice signal, and recognizes the speaker based on the multi-channel voice signal.

公开(公告)号：US11256906B2

公开(公告)日：2022-02-22

申请号：US17111907

申请日：2020-12-04

Applicant: Samsung Electronics Co., Ltd.

Inventor： Changyong Son ,  Wonsuk Chang ,  Deoksang Kim ,  Dae-Kyu Shin ,  Byungin Yoo ,  Seungju Han ,  Jaejoon Han ,  Jinwoo Son ,  Chang Kyu Choi

IPC: G06K9/00 ,  G06K9/78 ,  G06K9/62

Abstract: Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

公开(公告)号：US11151397B2

公开(公告)日：2021-10-19

申请号：US15156847

申请日：2016-05-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjun Kim ,  Sungjoo Suh ,  Jaejoon Han ,  Wonjun Hwang

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/55 ,  G06K9/46

Abstract: A user recognition method and apparatus, the user recognition method including performing a liveness test by extracting a first feature of a first image acquired by capturing a user, and recognizing the user by extracting a second feature of the first image based on a result of the liveness test, is provided.

公开(公告)号：US11093780B2

公开(公告)日：2021-08-17

申请号：US16437495

申请日：2019-06-11

Applicant: Samsung Electronics Co., Ltd. ,  Korea Advanced Institute of Science and Technology

Inventor： Byungin Yoo ,  Jun Ho Yim ,  Jun Mo Kim ,  Hee Chul Jung ,  Chang Kyu Choi ,  Jaejoon Han

IPC: G06K9/20 ,  G06T5/00 ,  G06T15/20 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62 ,  G06K9/00

Abstract: At least some example embodiments disclose a device and a method for generating a synthetic image and a different-angled image and eliminating noise. The method may include receiving input images, extracting feature values corresponding to the input images using an image learning model, the image learning model permitting an input and an output to be identical and generating a synthetic image based on the feature values corresponding to the input images using the image learning model.