专利检索 ap:("Samsung Electronics Co., Ltd." OR "Northeastern University") AND inv:"Ming Shao" 第 1 页

1.

发明申请
METHOD OF EXTRACTING FEATURE OF IMAGE TO RECOGNIZE OBJECT 审中-公开

公开(公告)号：US20170236000A1

公开(公告)日：2017-08-17

申请号：US15268988

申请日：2016-09-19

申请人： Samsung Electronics Co., Ltd. , Northeastern University

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

IPC分类号： G06K9/00 , G06K9/62

CPC分类号： G06K9/00268 , G06K9/00228 , G06K9/00275 , G06K9/00288 , G06K9/6215 , G06K9/6234 , G06K9/6269

摘要： 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.

2.

发明授权
Method of extracting feature of image to recognize object 有权

公开(公告)号：US10395098B2

公开(公告)日：2019-08-27

申请号：US15268988

申请日：2016-09-19

申请人： Samsung Electronics Co., Ltd.

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

IPC分类号： G06K9/62 , G06K9/00

摘要： 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.