公开(公告)号：US11347973B2

公开(公告)日：2022-05-31

申请号：US16595774

申请日：2019-10-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seon Min Rhee ,  Minsu Ko ,  Jihye Kim ,  Byung In Yoo ,  Chang Kyu Choi ,  Jaejoon Han

IPC: G06T15/00 ,  G06K9/36 ,  G06K9/62 ,  G06N20/00 ,  G06F21/32 ,  G06V40/50 ,  G06V40/16

Abstract: An apparatus for training an image generative model and an image generating apparatus are provided. The apparatus generates output images from a plurality of input images based on the generative model, extracts depth features from the respective output images based on a depth classification model, calculates a depth loss from the extracted depth features, and trains the generative model based on an overall loss that includes the calculated depth loss.

公开(公告)号：US10769255B2

公开(公告)日：2020-09-08

申请号：US15270172

申请日：2016-09-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungbae Kim ,  Seon Min Rhee ,  Jaejoon Han

IPC: G06F21/00 ,  G06F21/32 ,  G06F16/23 ,  G06F16/51 ,  G06K9/00 ,  G06K9/62 ,  G07C9/37 ,  G06F21/45 ,  G06F21/36 ,  G06K9/46 ,  H04L29/06

Abstract: A method of adaptively updating an enrollment database is disclosed. The method may include extracting a first feature vector from an input image, the input image including a face of a user, determining whether to enroll the input image in the enrollment database based on the first feature vector, second feature vectors of enrollment images and a representative vector, the second feature vectors of the enrollment images being enrolled in the enrollment database, and the representative vector representing the second feature vectors, and enrolling the input image in the enrollment database based on a result of the determining.

公开(公告)号：US20190244010A1

公开(公告)日：2019-08-08

申请号：US16390164

申请日：2019-04-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungbae Kim ,  Seon Min Rhee ,  Youngkyoo Hwang ,  Jaejoon Han

IPC: G06K9/00

CPC classification number: G06K9/00248 ,  G06K9/00208

Abstract: A method and an apparatus for registering a face, and a method and an apparatus for recognizing a face are disclosed, in which a face registering apparatus may change a stored three-dimensional (3D) facial model to an individualized 3D facial model based on facial landmarks extracted from two-dimensional (2D) face images, match the individualized 3D facial model to a current 2D face image of the 2D face images, and extract an image feature of the current 2D face image from regions in the current 2D face image to which 3D feature points of the individualized 3D facial model are projected, and a face recognizing apparatus may perform facial recognition based on image features of the 2D face images extracted by the face registering apparatus.

公开(公告)号：US10331941B2

公开(公告)日：2019-06-25

申请号：US15188437

申请日：2016-06-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seon Min Rhee ,  Jungbae Kim ,  Byungin Yoo ,  Jaejoon Han ,  Seungju Han

IPC: G06K9/00 ,  G06K9/62 ,  G06T19/20 ,  G06T15/04

Abstract: Face recognition of a face, to determine whether the face correlates with an enrolled face, may include generating a personalized three-dimensional (3D) face model based on a two-dimensional (2D) input image of the face, acquiring 3D shape information and a normalized 2D input image of the face based on the personalized 3D face model, generating feature information based on the 3D shape information and pixel color values of the normalized 2D input image, and comparing the feature information with feature information associated with the enrolled face. The feature information may include first and second feature information generated based on applying first and second deep neural network models to the pixel color values of the normalized 2D input image and the 3D shape information, respectively. The personalized 3D face model may be generated based on transforming a generic 3D face model based on landmarks detected in the 2D input image.

公开(公告)号：US11869272B2

公开(公告)日：2024-01-09

申请号：US16899935

申请日：2020-06-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngjun Kwak ,  Minsu Ko ,  Youngsung Kim ,  Heewon Kim ,  Ju Hwan Song ,  Byung In Yoo ,  Seon Min Rhee ,  Yong-il Lee ,  Jiho Choi ,  Seungju Han

IPC: G06V40/16 ,  G06T7/73 ,  G06F21/32 ,  G06T7/00 ,  G06V10/143 ,  G06V40/40

CPC classification number: G06V40/166 ,  G06F21/32 ,  G06T7/0012 ,  G06T7/73 ,  G06V10/143 ,  G06V40/161 ,  G06V40/168 ,  G06V40/40 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/30201

Abstract: A processor-implemented method includes: generating a preprocessed infrared (IR) image by performing first preprocessing based on an IR image including an object; generating a preprocessed depth image by performing second preprocessing based on a depth image including the object; and determining whether the object is a genuine object based on the preprocessed IR image and the preprocessed depth image.

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：US10860887B2

公开(公告)日：2020-12-08

申请号：US15347143

申请日：2016-11-09

Applicant: Samsung Electronics Co., Ltd.

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

IPC: G06K9/62 ,  G06K9/46 ,  G06K9/00 ,  G06N3/08 ,  H04L29/06

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：US10832030B2

公开(公告)日：2020-11-10

申请号：US15812484

申请日：2017-11-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seon Min Rhee ,  Kyuhong Kim ,  Changkyu Choi

IPC: G06K9/00 ,  G06K9/46

Abstract: A method of selecting a candidate fingerprint image for fingerprint recognition includes acquiring a target fingerprint image, generating a target frequency image based on a frequency conversion of the target fingerprint image, extracting frequency feature information associated with a representative frequency from the target frequency image, and selecting a candidate fingerprint image from enrolled fingerprint images by comparing the frequency feature information to enrolled frequency information.

公开(公告)号：US10769256B2

公开(公告)日：2020-09-08

申请号：US15469984

申请日：2017-03-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jaejoon Han ,  Jungbae Kim ,  Seon Min Rhee ,  Seungju Han ,  Minsu Ko

IPC: G06F21/00 ,  G06F21/32 ,  G06F16/23 ,  G06F16/51 ,  G06K9/00 ,  G06K9/62 ,  G07C9/37 ,  G06F21/45 ,  G06F21/36 ,  G06K9/46 ,  H04L29/06

Abstract: An adaptive updating method of an enrollment database is disclosed. The method may include extracting a first feature vector from an input image of a user, determining whether the input image is to be enrolled in an enrollment database based on the first feature vector, second feature vectors of enrollment images including initial enrollment images enrolled in the enrollment database, and a representative vector representing the initial enrollment images, and enrolling the input image in the enrollment database based on a result of the determining.

公开(公告)号：US09799140B2

公开(公告)日：2017-10-24

申请号：US14882624

申请日：2015-10-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngkyoo Hwang ,  Jungbae Kim ,  Seon Min Rhee ,  Jaejoon Han

IPC: G06T17/20 ,  G06K9/00 ,  G06T15/04 ,  G06T17/00

CPC classification number: G06T17/20 ,  G06K9/00208 ,  G06K9/00268 ,  G06K9/00281 ,  G06T15/04 ,  G06T17/00

Abstract: A method of generating a three-dimensional (3D) face model includes extracting feature points of a face from input images comprising a first face image and a second face image; deforming a generic 3D face model to a personalized 3D face model based on the feature points; projecting the personalized 3D face model to each of the first face image and the second face image; and refining the personalized 3D face model based on a difference in texture patterns between the first face image to which the personalized 3D face model is projected and the second face image to which the personalized 3D face model is projected.