公开(公告)号：US20170201676A1

公开(公告)日：2017-07-13

申请号：US15397992

申请日：2017-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ha-wook JEONG ,  Beom-su KIM ,  Sun-jung KIM ,  Hong-il KIM ,  Tae-hwa HONG

IPC: H04N5/232 ,  G06T7/143 ,  G06T7/149 ,  G06T7/11 ,  G06T7/13

CPC classification number: H04N5/23216 ,  G06T7/11 ,  G06T7/13 ,  G06T7/143 ,  G06T7/149 ,  G06T7/194 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20104 ,  G06T2207/30196 ,  H04N5/2258 ,  H04N5/23219 ,  H04N5/23293 ,  H04N5/2621

Abstract: Disclosed is an image processing apparatus including: a storage configured to store model information regarding a boundary of a person area in an image; and a controller configured to determine a boundary of a target area in an area to be processed, and to control the target area to undergo image processing for the person area if it is determined, based on the model information stored in the storage, that the determined boundary of the target area matches the boundary of the person area.

公开(公告)号：US20170104920A1

公开(公告)日：2017-04-13

申请号：US15290640

申请日：2016-10-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sun-jung KIM ,  Beom-su KIM ,  Hong-il KIM ,  Tae-hwa HONG ,  Joo-young SON

IPC: H04N5/232 ,  G06T7/40 ,  G06K9/66 ,  G06K9/00 ,  G06K9/52 ,  G06K9/46 ,  G06T7/20 ,  G06T7/00

CPC classification number: H04N5/23212 ,  G06K9/00228 ,  G06K9/00268 ,  G06K9/32 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/6224 ,  G06K9/66 ,  G06K9/78 ,  G06T7/162 ,  G06T7/194 ,  G06T7/20 ,  G06T7/215 ,  G06T2207/10024 ,  G06T2207/20036 ,  G06T2207/20076 ,  G06T2207/30196 ,  G06T2207/30201

Abstract: An imaging apparatus and a control method thereof are provided. The method for controlling the imaging apparatus includes acquiring images having a same focal length by performing continuous imaging in a predetermined time when a user's imaging command is input, calculating motion vectors using the images and separating a foreground and a background of a first image among the images based on the calculated motion vectors and color information of the first image, and performing out focusing based on the separated foreground and the separated background.

公开(公告)号：US20150093033A1

公开(公告)日：2015-04-02

申请号：US14499925

申请日：2014-09-29

Applicant: Samsung Electronics Co., Ltd. ,  Seoul National University R&DB Foundation

Inventor： Mu-sik KWON ,  Nam-ik CHO ,  Sang-ho KIM ,  Beom-su KIM ,  Won-kyo SEO

IPC: G06K9/00 ,  G06K9/46

CPC classification number: G06K9/00442 ,  G06K2009/363 ,  G06T3/0031 ,  G06T5/006

Abstract: A method and apparatus for generating a dewarped document using a document image captured using a camera are provided. The method includes obtaining the document image captures using the camera, extracting text lines from the document image captured using the camera, determining a projection formula to convert positions of respective points constituting the extracted text lines to coordinates projected on a plane of the dewarped document, determining a target function used to calculate a difference between text lines projected on the place of the dewarped document using the projection formula and real text lines, calculating parameters that minimize the target function, and converting the document image to the dewarped document by substituting the calculated parameters into the projection formula.

Abstract translation: 提供了使用使用相机拍摄的文档图像来生成杜瓦德文档的方法和装置。 该方法包括使用相机获得文档图像捕获，从使用相机拍摄的文档图像中提取文本行，确定投影公式以将构成所提取的文本行的各个点的位置转换为在已抹布的文档的平面上投影的坐标， 确定用于使用投影公式和实际文本行计算投影在杜瓦德文档的位置上的文本行之间的差异的目标函数，计算使目标函数最小化的参数，以及将文档图像转换为杜瓦德文档， 参数进入投影公式。

公开(公告)号：US20150071500A1

公开(公告)日：2015-03-12

申请号：US14477151

申请日：2014-09-04

Applicant: Samsung Electronics Co., Ltd. ,  Seoul National University R&DB Foundation

Inventor： Sang-ho KIM ,  Nam-ik CHO ,  Mu-sik KWON ,  Beom-su KIM ,  Won-kyo SEO

IPC: G06K9/00 ,  G06T5/00 ,  G06K9/46

CPC classification number: G06K9/00449 ,  G06K9/00463 ,  G06K9/4638 ,  G06T5/002 ,  G06T2207/10008 ,  G06T2207/20182 ,  G06T2207/30176

Abstract: A method of recognizing and generating a structure of a table included in an image is provided. The method includes extracting lines forming the table from among connection components forming an image, determining line intersections by using crossing functions matched with the lines, determining one of a plurality of crossing models identified based on a plurality of crossing shapes, in correspondence with each of the line intersections, and generating data about the table, which includes at least one cell determined using the determined crossing model.

Abstract translation: 提供一种识别和生成包括在图像中的表的结构的方法。 该方法包括从形成图像的连接部件中提取形成表的线，通过使用与线匹配的交叉函数来确定线交点，确定基于多个交叉形状识别的多个交叉模型之一， 线交叉点，以及生成关于该表的数据，其包括使用所确定的交叉模型确定的至少一个小区。