公开(公告)号：US20190087602A1

公开(公告)日：2019-03-21

申请号：US16116901

申请日：2018-08-29

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： So Hee PARK ,  Geonwoo KIM

IPC: G06F21/62 ,  H04N1/40 ,  G06F17/21 ,  G06F17/24 ,  G06F3/12

Abstract: An offline document de-identification apparatus and method, and an offline document restoration apparatus, are disclosed. The offline document de-identification apparatus may include an image obtainer acquiring offline document as an image, a document area detector detecting a document area in the acquired image, a de-identifier performing de-identification on a first area which is an area including the personal information in the document area, and a printer outputting document including the de-identified first area.

公开(公告)号：US20150332476A1

公开(公告)日：2015-11-19

申请号：US14140866

申请日：2013-12-26

Applicant: Electronics and Telecommunications Research Institute

Inventor： So Hee PARK ,  Jong Gook KO ,  Ki Young MOON ,  Jang Hee YOO

IPC: G06T7/20 ,  H04N7/18 ,  G06K9/00 ,  H04N5/232 ,  H04N5/247

CPC classification number: G06K9/00295 ,  G06K9/00335 ,  G06T7/246 ,  G06T7/292 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30232 ,  H04N5/23296 ,  H04N5/247 ,  H04N7/181 ,  H04N7/188

Abstract: The present invention relates to a method of tracking an object in a multiple cameras environment and the method includes generating first feature information of the object from an image input from a first camera; detecting a second camera in which identification information for the object is recognized when the object moves out of a view angle of the first camera, and comparing second feature information of the object generated from an image input from the second camera with the first feature information to track the object from the image input from the second camera. According to the present invention, the object is tracked based on an image in one camera image and if the object moves out of the camera, the identification information of the terminal which is possessed by the object is recognized to hand over the camera to continuously track the same object.

Abstract translation: 本发明涉及一种跟踪多个摄像机环境中的物体的方法，该方法包括从第一照相机输入的图像生成物体的第一特征信息; 检测第二相机，其中当对象移出第一相机的视角时，识别对象的识别信息，并且将从第二相机输入的图像生成的对象的第二特征信息与第一特征信息相比较， 从第二台相机的图像输入跟踪物体。 根据本发明，基于一个摄像机图像中的图像来跟踪对象，并且如果对象移出相机，则识别出被摄体所拥有的终端的识别信息，以切换相机以连续跟踪 同一个对象。

公开(公告)号：US20200236302A1

公开(公告)日：2020-07-23

申请号：US16749762

申请日：2020-01-22

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： So Hee PARK

IPC: H04N5/262 ,  H04N19/176 ,  H04N5/272 ,  G06K9/32

Abstract: A system for processing a masking region includes a transmitter configured to detect an object region, on which masking is to be performed, from an input image through a camera, convert the detected object region into a block region to perform masking, and encode and transmit an input image on which the masking is completed and a receiver configured to decode an image transmitted from the transmitted to extract a frame therefrom, detect a masked block region by units of extracted frames, and unmask the detected block region to restore the masked image to an original image.

公开(公告)号：US20140089236A1

公开(公告)日：2014-03-27

申请号：US13733407

申请日：2013-01-03

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Yong Jin LEE ,  So Hee PARK ,  Jong Gook KO ,  Ki Young MOON ,  Jang Hee YOO

IPC: G06N99/00

CPC classification number: G06N20/00 ,  G06K9/6231 ,  G06K9/6235 ,  G06K9/6256 ,  G06K9/6282 ,  G06K2009/6236

Abstract: Disclosed is a learning method using extracted data features for simplifying a learning process or improving accuracy of estimation. The learning method includes dividing input learning data into two groups based on a predetermined reference, extracting data features for distinguishing the two divided groups, and performing learning using the extracted data features.

Abstract translation: 公开了一种使用提取的数据特征来简化学习过程或提高估计精度的学习方法。 该学习方法包括基于预定参考将输入学习数据分成两组，提取用于区分两个分组的数据特征，以及使用所提取的数据特征进行学习。