公开(公告)号：US09697609B2

公开(公告)日：2017-07-04

申请号：US14289915

申请日：2014-05-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Won Jun Kim ,  Byung In Yoo ,  Chang Kyu Choi

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/73

CPC classification number: G06T7/75 ,  G06K9/00342 ,  G06K9/00369 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30196

Abstract: A method and apparatus for estimating a pose that estimates a pose of a user using a depth image is provided, the method including, recognizing a pose of a user from a depth image, and tracking the pose of the user using a user model exclusively of one another to enhance precision of estimating the pose.

公开(公告)号：US20170063851A1

公开(公告)日：2017-03-02

申请号：US15001548

申请日：2016-01-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjun Kim ,  Chilhee Chung ,  Jung-Bae Kim ,  Chang Kyu Choi ,  Seungju Han

IPC: H04L29/06 ,  H04M1/673 ,  H04W12/06 ,  G06K9/00 ,  G06F3/044

Abstract: A fingerprint recognition based authentication method and apparatus is disclosed. The authentication apparatus may obtain an input fingerprint from a touch input of a user, determine an input number corresponding to the input fingerprint using preregistered fingerprint-number mapping information, and authenticate the user based on whether an input number sequence corresponding to an input fingerprint sequence is identical to a reference number sequence.

Abstract translation: 公开了一种基于指纹识别的认证方法和装置。 认证装置可以从用户的触摸输入获得输入的指纹，使用预先登记的指纹号码映射信息确定与输入的指纹对应的输入号码，并根据输入的指纹序列对应的输入号码顺序对用户进行认证 与参考号序列相同。

公开(公告)号：US20170004346A1

公开(公告)日：2017-01-05

申请号：US15099994

申请日：2016-04-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Namjoon Kim ,  Sungjoo Suh ,  Wonjun Kim ,  Hyunjeong Lee ,  Chang Kyu Choi

IPC: G06K9/00 ,  G06K9/62 ,  G06F17/30 ,  G06K9/46

CPC classification number: G06F16/5866 ,  G06K9/00026 ,  G06K9/00926

Abstract: A fingerprint recognition method includes generating an enrollment modified image by modifying a fingerprint image corresponding to a fingerprint to be enrolled; extracting enrollment property information from the fingerprint image; generating mapping information that maps the enrollment modified image to the enrollment property information; and storing the enrollment modified image and the enrollment property information.

Abstract translation: 指纹识别方法包括通过修改与要登记的指纹相对应的指纹图像来生成注册修改图像; 从指纹图像提取注册属性信息; 生成将注册修改图像映射到注册属性信息的映射信息; 并存储注册修改图像和登记属性信息。

公开(公告)号：US09508152B2

公开(公告)日：2016-11-29

申请号：US14345563

申请日：2013-01-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Byung In Yoo ,  Chang Kyu Choi ,  Chang Kyo Lee ,  Jae Joon Han

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

CPC classification number: G06T7/0046 ,  G06K9/00201 ,  G06K9/00335 ,  G06K9/00362 ,  G06K9/469 ,  G06K9/6212 ,  G06K9/624 ,  G06K9/626 ,  G06K9/6282 ,  G06T7/75 ,  G06T15/06 ,  G06T15/08 ,  G06T15/20 ,  G06T15/40 ,  G06T17/005 ,  G06T2200/24 ,  G06T2207/10028 ,  G06T2207/20048 ,  G06T2207/20081 ,  G06T2207/30196

Abstract: An object recognition system is provided. The object recognition system for recognizing an object may include an input unit to receive, as an input, a depth image representing an object to be analyzed, and a processing unit to recognize a visible object part and a hidden object part of the object, from the depth image, by using a classification tree. The object recognition system may include a classification tree learning apparatus to generate the classification tree.

Abstract translation: 提供了一种物体识别系统。 用于识别对象的对象识别系统可以包括：输入单元，用于接收表示要分析的对象的深度图像作为输入;以及处理单元，用于识别对象的可见对象部分和隐藏对象部分， 深度图像，通过使用分类树。 对象识别系统可以包括生成分类树的分类树学习装置。

公开(公告)号：US09222767B2

公开(公告)日：2015-12-29

申请号：US13726808

申请日：2012-12-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sung Joo Suh ,  Kwon Ju Yi ,  Chang Kyu Choi ,  Du Sik Park

IPC: G06T15/00 ,  G01B11/22 ,  H04N5/222 ,  G06F3/042 ,  G06F3/03 ,  G01B11/02

CPC classification number: G06T7/74 ,  G01B11/026 ,  G01B11/22 ,  G06F3/0325 ,  G06F3/0425 ,  G06T7/571 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20024 ,  G06T2207/20228 ,  H04N5/2226

Abstract: A display apparatus and method may be used to estimate a depth distance from an external object to a display panel of the display apparatus. The display apparatus may acquire a plurality of images by detecting lights that are input from an external object and passed through apertures formed in a display panel, may generate one or more refocused images, and may calculate a depth from the external object to the display panel using the plurality of images acquired and one or more refocused images.

Abstract translation: 可以使用显示装置和方法来估计从外部物体到显示装置的显示面板的深度距离。 显示装置可以通过检测从外部物体输入并穿过形成在显示面板中的孔的光来获取多个图像，可以生成一个或多个重新聚焦图像，并且可以计算从外部对象到显示面板的深度 使用所获取的多个图像和一个或多个重聚焦图像。

公开(公告)号：US20140333722A1

公开(公告)日：2014-11-13

申请号：US14055369

申请日：2013-10-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Nam Joon KIM ,  Byung In Yoo ,  Sung Joo Suh ,  Chang Kyu Choi

IPC: H04N13/02

CPC classification number: H04N13/128 ,  G06T3/00 ,  G06T7/73 ,  G06T19/20 ,  G06T2207/10028 ,  G06T2207/30244 ,  G06T2219/2016

Abstract: An apparatus for processing a depth image using a relative angle between an image sensor and a target object includes an object image extractor to extract an object image from the depth image, a relative angle calculator to calculate a relative angle between an image sensor used to photograph the depth image and a target object corresponding to the object image, and an object image rotator to rotate the object image based on the relative angle and a reference angle.

Abstract translation: 用于使用图像传感器和目标对象之间的相对角度处理深度图像的装置包括从深度图像提取对象图像的对象图像提取器，用于计算用于拍摄的图像传感器之间的相对角度的相对角度计算器 所述深度图像和与所述对象图像对应的目标对象以及基于所述相对角度和参考角度旋转所述对象图像的对象图像旋转体。

公开(公告)号：US20140132530A1

公开(公告)日：2014-05-15

申请号：US13935688

申请日：2013-07-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sung Joo SUH ,  Chang Kyu Choi ,  Du Sik Park

IPC: G06F3/041 ,  H01L51/56 ,  G06F3/00

CPC classification number: G06F3/0412 ,  G06F3/0421 ,  H01L27/3223 ,  H04N1/00347 ,  H04N1/107 ,  H04N1/19584 ,  H04N2201/0081 ,  H04N2201/0089

Abstract: A display device, and a method of operating and manufacturing the display device may receive input light from an object to be scanned that is positioned in front of a display for displaying an image, and may perform scanning of the object to be scanned.

Abstract translation: 显示装置以及操作和制造显示装置的方法可以从位于显示器前方的待扫描物体接收输入光，并且可以对被扫描对象进行扫描。

公开(公告)号：US12293765B2

公开(公告)日：2025-05-06

申请号：US18317503

申请日：2023-05-15

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  SNU R&DB FOUNDATION

Inventor： Seungju Han ,  Jaejoon Han ,  Minsu Ko ,  Chang Kyu Choi ,  Bohyung Han

IPC: G10L17/02 ,  G06F18/20 ,  G06F18/24 ,  G06F21/36 ,  G06F21/45 ,  G06N3/045 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V40/50 ,  G06V40/70 ,  G10L17/04 ,  G10L17/06 ,  G10L17/18

Abstract: An authentication method and apparatus using a transformation model are disclosed. The authentication method includes generating, at a first apparatus, a first enrolled feature based on a first feature extractor, obtaining a second enrolled feature to which the first enrolled feature is transformed, determining an input feature by extracting a feature from input data with a second feature extractor different from the first feature extractor, and performing an authentication based on the second enrolled feature and the input feature.

公开(公告)号：US12118764B2

公开(公告)日：2024-10-15

申请号：US17177702

申请日：2021-02-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehyoung Yoo ,  Changyong Son ,  Dongwook Lee ,  Jaejoon Han ,  Chang Kyu Choi

IPC: G06V10/44 ,  G06N3/045 ,  G06N3/08 ,  H04N23/611 ,  H04N23/65 ,  H04N23/667 ,  H04N23/695

CPC classification number: G06V10/44 ,  G06N3/045 ,  G06N3/08 ,  H04N23/611 ,  H04N23/651 ,  H04N23/667 ,  H04N23/695

Abstract: A method and apparatus for processing an image based on partial images. The method includes extracting a feature of a current partial processing region of an input image frame by inputting pixel data of the current partial processing region into a convolutional neural network (CNN), updating a hidden state of a recurrent neural network (RNN) for a context between the current partial processing region and at least one previous partial processing region by inputting the extracted feature into the RNN, and generating an image processing result for the input image frame based on the updated hidden state.

公开(公告)号：US11971924B2

公开(公告)日：2024-04-30

申请号：US17508001

申请日：2021-10-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Youngjun Kwak ,  Byung In Yoo ,  Youngsung Kim ,  Chang Kyu Choi ,  Jaejoon Han

IPC: G06K9/00 ,  G06F16/00 ,  G06F16/583 ,  G06F18/22 ,  G06F18/2413 ,  G06F21/32 ,  G06F21/62 ,  G06N3/02 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V40/16 ,  G06V40/40 ,  G06V40/50 ,  G06N3/045 ,  G06T7/60 ,  G06T7/70

CPC classification number: G06F16/583 ,  G06F16/00 ,  G06F18/22 ,  G06F18/24137 ,  G06F21/32 ,  G06F21/6218 ,  G06N3/02 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V40/161 ,  G06V40/168 ,  G06V40/45 ,  G06V40/50 ,  G06N3/045 ,  G06T7/60 ,  G06T7/70 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A processor-implemented liveness test method includes detecting a face region in a query image, the query image including a test object for a liveness test, determining a liveness test condition to be applied to the test object among at least one liveness test condition for at least one registered user registered in a registration database, determining at least one test region in the query image based on the detected face region and the determined liveness test condition, obtaining feature data of the test object from image data of the determined at least one test region using a neural network-based feature extractor, and determining a result of the liveness test based on the obtained feature data and registered feature data registered in the registration database and corresponding to the determined liveness test condition.