-
公开(公告)号:US11093805B2
公开(公告)日:2021-08-17
申请号:US16426315
申请日:2019-05-30
Applicant: Samsung Electronics Co., Ltd.
Inventor: Seungju Han , Sungjoo Suh , Jaejoon Han , Chang Kyu Choi
Abstract: A method of recognizing a feature of an image may include receiving an input image including an object; extracting first feature information using a first layer of a neural network, the first feature information indicating a first feature corresponding to the input image among a plurality of first features; extracting second feature information using a second layer of the neural network, the second feature information indicating a second feature among a plurality of second features, the indicated second feature corresponding to the first feature information; and recognizing an element corresponding to the object based on the first feature information and the second feature information.
-
公开(公告)号:US10817704B2
公开(公告)日:2020-10-27
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:US10789455B2
公开(公告)日:2020-09-29
申请号:US16148587
申请日:2018-10-01
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Byungin Yoo , Youngjun Kwak , Jungbae Kim , Jinwoo Son , Changkyo Lee , Chang Kyu Choi , Jaejoon Han
Abstract: A liveness test method and apparatus is disclosed. A processor implemented liveness test method includes extracting an interest region of an object from a portion of the object in an input image, performing a liveness test on the object using a neural network model-based liveness test model, the liveness test model using image information of the interest region as provided first input image information to the liveness test model and determining liveness based at least on extracted texture information from the information of the interest region by the liveness test model, and indicating a result of the liveness test.
-
公开(公告)号:US10726261B2
公开(公告)日:2020-07-28
申请号:US15791846
申请日:2017-10-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Hyunjeong Lee , Sungjoo Suh , Changyong Son , Chang Kyu Choi , Jaejoon Han
Abstract: Disclosed is a user recognition apparatus and method, the apparatus configured to determine a validity of an iris area for each frame, to perform an iris recognition when the iris area is valid, and to extract a facial feature for a fusion recognition when the iris area is invalid.
-
公开(公告)号:US10395098B2
公开(公告)日:2019-08-27
申请号:US15268988
申请日:2016-09-19
Applicant: Samsung Electronics Co., Ltd.
Inventor: Wonjun Hwang , Sungjoo Suh , Jaejoon Han , Chang Kyu Choi , Yun Fu , Zhengming Ding , Ming Shao
Abstract: A method of converting a vector corresponding to an input image includes receiving input vector data associated with an input image including an object; and converting the received input vector data into feature data based on a projection matrix having a fixed rank, wherein a first dimension of the input vector data is higher than a second dimension of the feature data.
-
公开(公告)号:US10360469B2
公开(公告)日:2019-07-23
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
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.
-
公开(公告)号:US10248844B2
公开(公告)日:2019-04-02
申请号:US15189454
申请日:2016-06-22
Applicant: Samsung Electronics Co., Ltd.
Inventor: Jungbae Kim , Ruslan Salakhutdinov , Jaejoon Han , Byungin Yoo
Abstract: A training method of training an illumination compensation model includes extracting, from a training image, an albedo image of a face area, a surface normal image of the face area, and an illumination feature, the extracting being based on an illumination compensation model; generating an illumination restoration image based on the albedo image, the surface normal image, and the illumination feature; and training the illumination compensation model based on the training image and the illumination restoration image.
-
公开(公告)号:US10121059B2
公开(公告)日:2018-11-06
申请号:US15656350
申请日:2017-07-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Byungin Yoo , Youngjun Kwak , Jungbae Kim , Jinwoo Son , Changkyo Lee , Chang Kyu Choi , Jaejoon Han
Abstract: A liveness test method and apparatus is disclosed. A processor implemented liveness test method includes extracting an interest region of an object from a portion of the object in an input image, performing a liveness test on the object using a neural network model-based liveness test model, the liveness test model using image information of the interest region as provided first input image information to the liveness test model and determining liveness based at least on extracted texture information from the information of the interest region by the liveness test model, and indicating a result of the liveness test.
-
公开(公告)号:US10097808B2
公开(公告)日:2018-10-09
申请号:US15019046
申请日:2016-02-09
Applicant: Samsung Electronics Co., Ltd.
Inventor: Hui Zhang , Yongjie Zhang , Fei Duan , Haoxing Wang , Jaejoon Han , Jungbae Kim , Meng Ye , Seon Min Rhee
IPC: G06K9/00 , H04N13/128 , H04N13/271 , G06T7/593 , H04N13/00
Abstract: An apparatus and corresponding method are provided to match images and include assigning depth candidate values to a pixel in a first image, and reassigning third depth candidate values to a first pixel in the first image based on first depth candidate values assigned to the first pixel and second depth candidate values assigned to a second pixel adjacent to the first pixel. The apparatus and method also include determining one of the third depth candidate values to be a depth value of the first pixel, and matching the first pixel and a third pixel in a second image corresponding to the determined depth value of the first pixel.
-
公开(公告)号:US10083343B2
公开(公告)日:2018-09-25
申请号:US14795002
申请日:2015-07-09
Applicant: Samsung Electronics Co., Ltd.
Inventor: Sungjoo Suh , Wonjun Hwang , Wonjun Kim , Jaejoon Han
CPC classification number: G06K9/00221 , G06K9/00228 , G06K9/00248 , G06K9/00281 , G06K9/00288 , G06K9/6209 , G06K9/6278 , G06K9/6296 , G06K2209/21
Abstract: At least some example embodiments disclose a method and apparatus for facial recognition. The facial recognition method includes detecting initial landmarks from a facial image, first normalizing the facial image using the initial landmarks, updating a position of at least one of intermediate landmarks based on the first normalizing, the intermediate landmarks being landmarks transformed from the initial landmarks through the first normalizing, second normalizing the facial image after the updating and recognizing a face using a feature of the second normalized facial image.
-
-
-
-
-
-
-
-
-