公开(公告)号：US20170236000A1

公开(公告)日：2017-08-17

申请号：US15268988

申请日：2016-09-19

Applicant: Samsung Electronics Co., Ltd. ,  Northeastern University

Inventor： Wonjun Hwang ,  Sungjoo Suh ,  Jaejoon Han ,  Chang Kyu Choi ,  Yun Fu ,  Zhengming Ding ,  Ming Shao

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00268 ,  G06K9/00228 ,  G06K9/00275 ,  G06K9/00288 ,  G06K9/6215 ,  G06K9/6234 ,  G06K9/6269

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：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

IPC: G06K9/62 ,  G06K9/00

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：US09959457B2

公开(公告)日：2018-05-01

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 ,  Jae-Joon Han

IPC: G06K9/00 ,  G06K9/62

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.