-
公开(公告)号:US20230051648A1
公开(公告)日:2023-02-16
申请号:US17975837
申请日:2022-10-28
Applicant: Samsung Electronics Co., Ltd.
Inventor: Jinwoo SON , Changyong SON , Jaejoon HAN , Chang Kyu CHOI
Abstract: Disclosed is a convolutional neural network (CNN) processing apparatus and method, the apparatus configured to determine a loading space unit for at least one loading space in an input based on a height or a width for an input feature map of the input and an extent of a dimension of a kernel feature map, load target input elements corresponding to a target loading space, among the at least one loading space, from a memory and store the target input elements in an allocated input buffer having a size corresponding to the loading space unit, and perform a convolution operation between the target input elements stored in the input buffer and at least one kernel element of a kernel.
-
公开(公告)号:US20220138576A1
公开(公告)日:2022-05-05
申请号:US17574408
申请日:2022-01-12
Applicant: Samsung Electronics Co., Ltd.
Inventor: Changyong SON , Jinwoo SON , Byungin YOO , Chang Kyu CHOI , Jae-Joon HAN
Abstract: A lightened neural network method and apparatus. The neural network apparatus includes a processor configured to generate a neural network with a plurality of layers including plural nodes by applying lightened weighted connections between neighboring nodes in neighboring layers of the neural network to interpret input data applied to the neural network, wherein lightened weighted connections of at least one of the plurality of layers includes weighted connections that have values equal to zero for respective non-zero values whose absolute values are less than an absolute value of a non-zero value. The lightened weighted connections also include weighted connections that have values whose absolute values are no greater than an absolute value of another non-zero value, the lightened weighted connections being lightened weighted connections of trained final weighted connections of a trained neural network whose absolute maximum values are greater than the absolute value of the other non-zero value.
-
公开(公告)号:US20210089755A1
公开(公告)日:2021-03-25
申请号:US17111912
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
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: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
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:US20200210556A1
公开(公告)日:2020-07-02
申请号:US16545095
申请日:2019-08-20
Applicant: Samsung Electronics Co., Ltd.
Inventor: Dohwan LEE , Kyuhong KIM , Chang Kyu CHOI
Abstract: A user verification method and apparatus using a generalized user model is disclosed, where the user verification method includes generating a feature vector corresponding to a user based on input data corresponding to the user, determining a first parameter indicating a similarity between the feature vector and an enrolled feature vector enrolled for user verification, determining a second parameter indicating a similarity between the feature vector and a user model corresponding to generalized users, and verifying the user based on the first parameter and the second parameter.
-
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:US20180285629A1
公开(公告)日:2018-10-04
申请号:US15864232
申请日:2018-01-08
Applicant: Samsung Electronics Co., Ltd.
Inventor: Changyong SON , Deoksang KIM , Minsu KO , Jinwoo SON , Seungju HAN , Chang Kyu CHOI , Jae-Joon HAN
Abstract: A face verification method and apparatus is disclosed. The face verification method includes selecting a current verification mode, from among plural verification modes, to be implemented for the verifying of the face, determining one or more recognizers, from among plural recognizers, based on the selected current verification mode, extracting feature information from information of the face using at least one of the determined one or more recognizers, and indicating whether a verification is successful based on the extracted feature information.
-
公开(公告)号:US20180253210A1
公开(公告)日:2018-09-06
申请号:US15966286
申请日:2018-04-30
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Keun Joo PARK , Hyun Surk RYU , Chang Kyu CHOI , Joon Ah PARK
IPC: G06F3/0488 , G06F3/03 , G06F3/01
CPC classification number: G06F3/0488 , G06F3/017 , G06F3/0304 , G06F2203/04802
Abstract: A method of displaying a menu based on at least one of a depth information and a space gesture is provided. The method including determining depth information corresponding to a distance from a screen of a user terminal to a hand of a user; identifying at least one layer among a plurality of layers based on the depth information; and applying a graphic effect to the identified layer so that a menu page corresponding to the at least one identified layer is displayed on the screen of the user terminal.
-
公开(公告)号:US20180144185A1
公开(公告)日:2018-05-24
申请号:US15626440
申请日:2017-06-19
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Byungin YOO , Youngjun KWAK , Youngsung KIM , Seonmin RHEE , Chang Kyu CHOI
CPC classification number: G06K9/00308 , G06K9/00228 , G06K9/00255 , G06K9/00288 , G06K9/00302 , G06K9/6256 , G06K9/66
Abstract: A facial expression recognition method includes actuating a processor to acquire an input image including an object; and identifying a facial expression intensity of the object from the input image based on a facial expression recognition model.
-
公开(公告)号:US20180137388A1
公开(公告)日:2018-05-17
申请号:US15795677
申请日:2017-10-27
Applicant: Samsung Electronics Co., Ltd.
Inventor: Youngsung KIM , Byungin YOO , Deheng QIAN , Hui ZHANG , Chang Kyu CHOI , He ZHENG , Jae-Joon HAN , Jingtao XU , Tianchu GUO
CPC classification number: G06K9/623 , G06K9/00281 , G06K9/00288 , G06K9/6265 , G06K9/627 , G06K9/6297 , G06K9/66 , G06N3/0454
Abstract: A method to analyze a facial image includes: inputting a facial image to a residual network including residual blocks that are sequentially combined and arranged in a direction from an input to an output; processing the facial image using the residual network; and acquiring an analysis map from an output of an N-th residual block among the residual blocks using a residual deconvolution network, wherein the residual network transfers the output of the N-th residual block to the residual deconvolution network, and N is a natural number that is less than a number of all of the residual blocks, and wherein the residual deconvolution network includes residual deconvolution blocks that are sequentially combined, and the residual deconvolution blocks correspond to respective residual blocks from a first residual block among the residual blocks to the N-th residual block.
-
-
-
-
-
-
-
-
-