公开(公告)号：US20200210685A1

公开(公告)日：2020-07-02

申请号：US16728056

申请日：2019-12-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minsu KO ,  Seungju HAN ,  Wonsuk CHANG ,  Jaejoon HAN ,  Seon Min RHEE ,  Chang Kyu CHOI

IPC: G06K9/00 ,  G06F21/32

Abstract: A processor-implemented verification method includes: detecting a characteristic of an input image; acquiring input feature transformation data and enrolled feature transformation data by respectively transforming input feature data and enrolled feature data based on the detected characteristic, wherein the input feature data is extracted from the input image using a feature extraction model; and verifying a user corresponding to the input image based on a result of comparison between the input feature transformation data and the enrolled feature transformation data.

公开(公告)号：US20190180128A1

公开(公告)日：2019-06-13

申请号：US16133976

申请日：2018-09-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seungju HAN ,  Minsu KO ,  Chang Kyu CHOI ,  Jaejoon HAN ,  Wonsuk CHANG

IPC: G06K9/00

Abstract: A user registration device and method is disclosed. The user registration device compares an initial image stored in a database and a newly input candidate image, and determines whether to generate and manage an additional database based on the similarity between the initial image and the candidate image.

公开(公告)号：US20190138792A1

公开(公告)日：2019-05-09

申请号：US16234720

申请日：2018-12-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungjoo SUH ,  Seungju HAN ,  Jaejoon HAN

IPC: G06K9/00

Abstract: At least one example embodiment discloses a method of extracting a feature from an input image. The method may include detecting landmarks from the input image, detecting physical characteristics between the landmarks based on the landmarks, determining a target area of the input image from which at least one feature is to be extracted and an order of extracting the feature from the target area based on the physical characteristics and extracting the feature based on the determining.

公开(公告)号：US20170154428A1

公开(公告)日：2017-06-01

申请号：US15237082

申请日：2016-08-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Changkyo LEE ,  Jaejoon HAN ,  Wonjun HWANG

IPC: G06T7/00 ,  G06K9/20 ,  G06K9/00

CPC classification number: G06T7/337 ,  G06K9/2054 ,  G06T7/0044 ,  G06T2207/30201 ,  G06T2207/30232

Abstract: An object detection method and apparatus are provided. The object detection method may include adaptively generating a pyramid image corresponding to a current frame based on information associated with a target object detected from a previous frame.

公开(公告)号：US20170039357A1

公开(公告)日：2017-02-09

申请号：US15097555

申请日：2016-04-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjun HWANG ,  Wonjun KIM ,  Sungjoo SUH ,  Byungin YOO ,  Changkyu CHOI ,  Jaejoon HAN

IPC: G06F21/32 ,  G06F21/36

Abstract: A user authentication method includes receiving a first input image including information on a first modality; receiving a second input image including information on a second modality; determining at least one first score by processing the first input image based on at least one first classifier, the at least one first classifier being based on the first modality; determining at least one second score by processing the second input image based on at least one second classifier, the at least one second classifier being based on the second modality; and authenticating a user based on the at least one first score, the at least one second score, a first fusion parameter of the at least one first classifier, and a second fusion parameter of the at least one second classifier.

Abstract translation: 用户认证方法包括接收包括关于第一模态的信息的第一输入图像; 接收包括关于第二模态的信息的第二输入图像; 通过基于至少一个第一分类器处理所述第一输入图像来确定至少一个第一分数，所述至少一个第一分类器基于所述第一模态; 通过基于至少一个第二分类器处理所述第二输入图像来确定至少一个第二分数，所述至少一个第二分类器基于所述第二模态; 以及基于所述至少一个第一分数，所述至少一个第二分数，所述至少一个第一分类器的第一融合参数和所述至少一个第二分类器的第二融合参数来验证用户。

公开(公告)号：US20160210751A1

公开(公告)日：2016-07-21

申请号：US14994688

申请日：2016-01-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Xuetao FENG ,  Biao Wang ,  Hao Feng ,  Hongwei Zhang ,  Changkyu CHOI ,  Jaejoon HAN ,  Jungbae KIM ,  Lujin GONG

IPC: G06T7/00 ,  G06K9/62 ,  G06T5/00 ,  G06K9/46 ,  G06K9/48

CPC classification number: G06K9/4604 ,  G06K9/00214 ,  G06K9/00288 ,  G06K9/4652 ,  G06K9/481 ,  G06K9/6201 ,  G06K9/6206 ,  G06T7/33 ,  G06T2200/04 ,  G06T2207/10028 ,  G06T2207/30201

Abstract: Provided is a 3D registration method and apparatus that may select a key point from among plural points included in 3D target data, based on a geometric feature or a color feature of each of the plural points, may adjust a position of the selected key point of the 3D target data based on features of, or a distance between, a key point of the 3D source data and the selected key point of the 3D target data, may calculate reliabilities of plural key points of the 3D source data based on respective features of at least one key point of the 3D target data determined to correspond to the plural key points of the 3D source data, and may generate 3D registration data by performing 3D registration between the 3D source data and the 3D target data based on the calculated reliabilities.

Abstract translation: 提供了一种可以基于多个点中的每一个的几何特征或颜色特征来选择包括在3D目标数据中的多个点中的关键点的3D登记方法和装置，可以调整所选择的关键点的位置 基于3D源数据的关键点和3D目标数据的所选关键点之间的特征或距离的3D目标数据可以基于3D源数据的各个特征来计算3D源数据的多个关键点的可靠性 所述3D目标数据的至少一个关键点被确定为对应于所述3D源数据的所述多个关键点，并且可以基于所计算的可靠性通过在所述3D源数据和所述3D目标数据之间执行3D注册来生成3D注册数据。

公开(公告)号：US20160154994A1

公开(公告)日：2016-06-02

申请号：US14918783

申请日：2015-10-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungbae KIM ,  Seon Min RHEE ,  Youngkyoo HWANG ,  Jaejoon HAN

IPC: G06K9/00 ,  G06K9/62 ,  G06T7/00

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.

Abstract translation: 公开了一种用于登记脸部的方法和装置，以及用于识别脸部的方法和装置，其中面部登记装置可以将存储的三维（3D）面部模型改变为基于面部的个性化3D面部模型 从二维（2D）面部图像提取的地标，将个体化3D面部模型与2D脸部图像的当前2D脸部图像相匹配，并将当前2D脸部图像的图像特征从当前2D脸部图像中的区域提取到 投影个性化3D面部模型的3D特征点，面部识别装置可以基于面部登记装置提取的2D面部图像的图像特征进行面部识别。

公开(公告)号：US20160086047A1

公开(公告)日：2016-03-24

申请号：US14858082

申请日：2015-09-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungjoo SUH ,  Yun FU ,  Zhengming DING ,  Chang Kyu CHOI ,  Jaejoon HAN

IPC: G06K9/46 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06K9/00288 ,  G06K9/6247

Abstract: At least one example embodiment discloses a method of converting a vector corresponding to an input image. The method includes receiving first-dimensional vector data associated with an input image, the input image including an object and converting the received first-dimensional vector data to second-dimensional vector data based on a projection matrix with an associated rank. A first dimension of the first-dimensional vector data is higher than a second dimension of the second-dimensional vector data.

Abstract translation: 至少一个示例性实施例公开了一种转换对应于输入图像的向量的方法。 所述方法包括接收与输入图像相关联的第一维矢量数据，所述输入图像包括对象，并且基于具有关联等级的投影矩阵将所接收的第一维向量数据转换为第二维向量数据。 第一维矢量数据的第一尺寸高于第二维矢量数据的第二尺寸。

公开(公告)号：US20160086016A1

公开(公告)日：2016-03-24

申请号：US14816149

申请日：2015-08-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungjoo SUH ,  Seungju HAN ,  Jaejoon HAN

IPC: G06K9/00

CPC classification number: G06K9/00248

Abstract: At least one example embodiment discloses a method of extracting a feature from an input image. The method may include detecting landmarks from the input image, detecting physical characteristics between the landmarks based on the landmarks, determining a target area of the input image from which at least one feature is to be extracted and an order of extracting the feature from the target area based on the physical characteristics and extracting the feature based on the determining.

Abstract translation: 至少一个示例性实施例公开了一种从输入图像提取特征的方法。 该方法可以包括从输入图像中检测地标，基于地标检测地标之间的物理特征，确定要从中提取至少一个特征的输入图像的目标区域和从目标中提取特征的顺序 基于物理特征的区域和基于确定的特征提取。

公开(公告)号：US20160078282A1

公开(公告)日：2016-03-17

申请号：US14812252

申请日：2015-07-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Changkyo LEE ,  Byungin YOO ,  Namjoon KIM ,  Jaejoon HAN

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06K9/00268 ,  G06K9/4642 ,  G06K9/6202 ,  G06K9/6277 ,  G06K2009/4666

Abstract: At least one example embodiment discloses an image feature extracting method. The method includes determining a probabilistic model based on pixel values of pixels in a kernel, determining image feature information of a current pixel of the pixels in the kernel and determining whether to change the image feature information of the current pixel based on a random value and a probability value of the current pixel, the probability value being based on the probabilistic model.

Abstract translation: 至少一个示例性实施例公开了一种图像特征提取方法。 该方法包括基于内核中的像素的像素值确定概率模型，确定内核中的像素的当前像素的图像特征信息，并基于随机值确定是否改变当前像素的图像特征信息;以及 当前像素的概率值，概率值基于概率模型。