-
公开(公告)号：KR101805624B1
公开(公告)日：2017-12-08
申请号：KR1020110086695
申请日：2011-08-29
Applicant: 삼성전자주식회사
CPC classification number: G06K9/00 , G06T5/50 , G06T2207/10072 , G06T2207/30056
Abstract: 장기모델영상생성방법및 장치에따르면, 피검자신체내부를나타내는의료영상의영상데이터를입력받고, 입력된의료영상으로부터신체내부의소정장기를나타내는영상을추출하고, 추출된영상에기초하여장기의일반화된모델영상으로부터피검자의장기모델영상을생성하고, 생성된장기모델영상을출력한다.
Abstract translation: 根据长期模型中，图像产生方法和设备，所述对象接收表示身体内部的医用图像的图像数据，提取表示从输入的医用图像的预定器官的身体内部的图像，并且概括于基于所提取的图像在长期 根据模型图像生成对象的长期模型图像，并输出生成的长期模型图像。
-
公开(公告)号：KR101615719B1
公开(公告)日：2016-04-27
申请号：KR1020090088501
申请日：2009-09-18
Applicant: 삼성전자주식회사
CPC classification number: G06K9/00335 , G06K9/00315 , G06T13/40
Abstract: 사용자의 3차원얼굴표정추출방법및 장치를제안한다. 사용자의 3차원얼굴표정추출방법및 장치는사용자의얼굴영상을수신하면, 형상기반추적과텍스쳐기반추적을모두사용해서얼굴영상에서표정을추적해서 3차원표정정보를생성하고, 3차원표정정보가반영된 3차원표정모델을생성하고, 3차원표정모델에이마나볼 등의근육제어점들을추가해서자연스러운얼굴표정을가진 3차원표정모델로재구성할수 있다.
Abstract translation: 提供一种提取用户的3D面部表情的方法和装置。 当接收到用户的面部图像时，3D面部表情提取方法和装置可以通过使用基于形状的跟踪和基于纹理的跟踪中的至少一个来从面部图像跟踪用户的表情来生成3D表情信息， 基于3D表达信息生成3D表达模型，并通过将肌肉控制点添加到3D表达模型中，重建3D表达模型以具有自然的面部表情。
-
公开(公告)号：KR1020150027637A
公开(公告)日：2015-03-12
申请号：KR1020130106309
申请日：2013-09-04
Applicant: 삼성전자주식회사 , 사회복지법인 삼성생명공익재단
CPC classification number: A61B8/5261 , A61B5/0035 , A61B5/055 , A61B6/032 , A61B6/037 , A61B6/5247 , G06T7/11 , G06T7/136 , G06T7/143 , G06T7/187 , G06T7/33 , G06T2207/10072 , G06T2207/10136 , G06T2207/20101 , G06T2207/20221 , G06T2207/30056 , G06T2207/30101
Abstract: A method to match medical images according to an embodiment of the present invention includes the following steps of: selecting at least one point from a first medical image acquired in non-real time; respectively extracting an anatomical object including the selected point and an anatomical object positioned near the selected point from the first medical image; extracting anatomical objects corresponding to anatomical objects, extracted from the first medical image, from a second medical image acquired in real time; and matching the first medical image with the second medical image by using a geometric relation between anatomical objects extracted from the first medical image and the second medical image.
Abstract translation: 根据本发明的实施例的匹配医学图像的方法包括以下步骤：从非实时获取的第一医疗图像中选择至少一个点; 分别从所述第一医用图像提取包括所选择的解剖学对象和位于所述选定点附近的解剖学对象; 从实时获取的第二医疗图像中提取对应于从第一医学图像提取的解剖学对象的解剖学对象; 以及通过使用从第一医疗图像提取的解剖对象与第二医学图像之间的几何关系来匹配第一医学图像与第二医学图像。
-
公开(公告)号：KR101441585B1
公开(公告)日：2014-09-25
申请号：KR1020080040485
申请日：2008-04-30
Applicant: 삼성전자주식회사
IPC: H04N5/265
Abstract: 본 발명은 카메라 및 촬영이미지 합성방법에 관한 것으로, 본 발명의 일 실시예에 따른 촬영이미지 합성방법은 이미지 합성 모드에 진입되면 미리 촬영된 제1 이미지 및 제1 이미지와 동일한 배경에서 카메라에 포착되고 있는 제2 이미지를 분석하며, 분석된 결과에 따라 분할된 인물 이미지를 백그라운드 이미지에 오버레이하여 가이드 이미지를 제공한다.
카메라, 촬영이미지, 합성-
公开(公告)号：KR1020140105103A
公开(公告)日：2014-09-01
申请号：KR1020130018840
申请日：2013-02-21
Applicant: 삼성전자주식회사
CPC classification number: G06T7/246 , G06T2207/10081 , G06T2207/10088 , G06T2207/10116 , G06T2207/30004 , G06T2207/30241
Abstract: According to a method for tracking the motion of an organ, the organ shape data of a first subject to show the shape of the organ obtained in the moment of the preset motion of the first subject is received. First to N-th interpolation curves to show the track of the spatial and temporal motion of the organ of each subject obtained for the same types of organs of a plurality of subjects which are different from the first subject are loaded from a storage device. The interpolation curve of the first subject to show the track of the spatial and temporal motion of the organ of the first subject is estimated based on the first to N-th interpolation curves and the organ shape data of the first subject.
Abstract translation: 根据用于跟踪器官的运动的方法，接收第一受试者的器官形状数据，以示出在第一受试者的预设动作的时刻获得的脏器的形状。 从存储装置加载第一到第N插值曲线，以示出对于与第一对象不同的多个被摄体的相同类型的器官获得的每个被摄体的器官的空间和时间运动的轨迹。 基于第一至第N插值曲线和第一被摄体的器官形状数据来估计第一被摄体的显示第一被摄体的器官的空间和时间运动的轨迹的插值曲线。
-
Patent Agency Ranking
公开(公告)号：KR1020140055787A
公开(公告)日：2014-05-09
申请号：KR1020120123092
申请日：2012-11-01
Applicant: 삼성전자주식회사
CPC classification number: G06T7/0081 , G06T7/11 , G06T7/162 , G06T7/174 , G06T7/60 , G06T2207/10081 , G06T2207/10088 , G06T2207/30056
Abstract: A method to segment an object image included in an organ in an organ image according to an embodiment of the present invention comprises the following steps of: generating a reference model of an object using prior knowledge about the object included in an organ; obtaining a first image of the organ of a subject; determining the presence of a first area where the shape of the first object cannot be estimated in the obtained first image; and segmenting a second image of the object from the first image when the first area does not exist, and segmenting the second image from the first image by estimating the traveling direction of the first area from the reference model when the first area exists.
Abstract translation: 根据本发明的实施例的分割器官图像中的器官中包括的对象图像的方法包括以下步骤：使用关于包括在器官中的对象的先前知识来生成对象的参考模型; 获得受试者的器官的第一图像; 确定在所获得的第一图像中不能估计第一对象的形状的第一区域的存在; 以及当所述第一区域不存在时，从所述第一图像分割所述对象的第二图像，并且当所述第一区域存在时，从所述参考模型估计所述第一区域的行进方向，从所述第一图像分割所述第二图像。
-
公开(公告)号：KR101330636B1
公开(公告)日：2013-11-18
申请号：KR1020070007663
申请日：2007-01-24
Applicant: 삼성전자주식회사
CPC classification number: G06K9/00288 , G06K9/4614 , G06K9/6257
Abstract: 얼굴시점 결정장치 및 방법과 이를 채용하는 얼굴검출장치 및 방법이 개시된다. 얼굴검출장치는 현재 영상이 얼굴에 해당하는지 여부를 판단하는 비얼굴 판단 부; 상기 현재 영상이 얼굴에 해당하는 경우 상기 현재 영상에 대하여 적어도 하나 이상의 시점 클래스를 추정하는 시점 추정부; 및 상기 추정된 적어도 하나 이상의 시점 클래스를 독립적으로 검증하여 상기 현재 영상의 최종적인 시점 클래스를 결정하는 독립 시점 검증부로 이루어진다.
-
公开(公告)号：KR1020130023735A
公开(公告)日：2013-03-08
申请号：KR1020110086695
申请日：2011-08-29
Applicant: 삼성전자주식회사
CPC classification number: G06K9/00 , G06T5/50 , G06T2207/10072 , G06T2207/30056 , G06T17/10 , A61B5/055 , A61B6/03 , A61B8/00 , G06T17/00 , G06T17/20
Abstract: PURPOSE: An organ model image generating method and a device thereof are provided to generates an organ model of a testee to which characteristics of organs of the testees from a generalized model image of the organs determined from sample image data. CONSTITUTION: An input unit(21) receives a medical image of a testee from a medical image generating device. An organ image extracting unit(221) of an image processor(22) extracts an image indicating organs in a body of the testee from the medical image. An organ model image generating unit(222) of the image processor generates an organ model image of the testee from a generalized model image. An output unit(24) outputs image data of the generated organ model image to an image display device. [Reference numerals] (21) Input unit; (22) Image processor; (221) Organ image extracting unit; (222) Organ model image generating unit; (23) Storage unit; (24) Output unit; (25) User interface; (AA) Generalized model image; (BB) Medical image; (CC) Organ model image
Abstract translation: 目的：提供器官模型图像生成方法及其装置，以从样本图像数据确定的器官的广义模型图像生成受试者器官的特征的器官模型。 构成：输入单元（21）从医学图像生成装置接收受检者的医学图像。 图像处理器（22）的器官图像提取单元（221）从医学图像中提取被检查者的身体中指示器官的图像。 图像处理器的器官模型图像生成单元（222）从广义模型图像生成被测者的器官模型图像。 输出单元（24）将生成的器官模型图像的图像数据输出到图像显示装置。 （附图标记）（21）输入单元; （22）图像处理器; （221）器官图像提取单元; （222）器官模型图像生成单元; （23）存储单元; （24）输出单元; （25）用户界面; （AA）广义模型图像; （BB）医学图像; （CC）器官模型图像
-
公开(公告)号：KR1020120111871A
公开(公告)日：2012-10-11
申请号：KR1020110086694
申请日：2011-08-29
Applicant: 삼성전자주식회사
Abstract: PURPOSE: A method and apparatus for generating images of body organs using a 3D model are provided to accurately and rapidly track a position of a body organ during an interventional procedure by synthesizing a model of the body organ with medical images outputting in real time and by outputting a synthesized result. CONSTITUTION: An image detecting device(10) generates video data using a source signal which is generated from a probe(11). The image detecting device generates video data of a 3D volume which shows a specific site of a body of a patient in 3D. The probe is generally made of a piezoelectric transducer. An image matching device(20) outputs an image in which the model of lesion and the organ are matched from images detected in real time. An image display device(30) selects one from the matched images based on a current body state of the patient and outputs the matched image. [Reference numerals] (AA) Patient
Abstract translation: 目的：提供一种使用3D模型生成身体器官的图像的方法和装置，用于通过将实体输出的医学图像合成体内器官的模型，并通过实时输出的医学图像来精确地并且快速地跟踪身体器官在介入手术过程中的位置 输出合成结果。 构成：图像检测装置（10）使用从探头（11）生成的源信号来生成视频数据。 图像检测装置生成以3D显示患者身体的特定部位的3D体积的视频数据。 探针通常由压电换能器制成。 图像匹配装置（20）从实时检测到的图像输出病变和器官的模型匹配的图像。 图像显示装置（30）基于患者的当前身体状态从匹配图像中选择一个，并输出匹配图像。 （附图标记）（AA）患者
-
公开(公告)号：KR1020120059994A
公开(公告)日：2012-06-11
申请号：KR1020100121533
申请日：2010-12-01
Applicant: 삼성전자주식회사
CPC classification number: G06F3/012 , G06K9/00221 , G06K9/00302 , G06T2207/30196 , G06N3/004 , G06T7/0012
Abstract: PURPOSE: An avatar controlling apparatus and a method thereof are provided to extracts a feature point location capable of sensing an expression change of a user face without using a marker. CONSTITUTION: An expression tracing unit(102) traces a feature point location of a face expression from a face expression image of a user. A feature point position resetting unit(103) removes a head movement at the traced feature point location. The feature point position resetting unit resets a feature point location of the face expression. A control point generating unit(104) generates an expression control point by using an expression parameter.
Abstract translation: 目的：提供一种化身控制装置及其方法，以提取能够感测用户面部的表情变化而不使用标记的特征点位置。 构成：表情追踪单元（102）从用户的脸部表情图像中追踪面部表情的特征点位置。 特征点位置复位单元（103）去除跟踪的特征点位置处的头部移动。 特征点位置复位单元复位脸部表情的特征点位置。 控制点生成单元（104）通过使用表达式参数来生成表达式控制点。
-
-
-
-
-
-
-
-
-
Search Results
195
records
(took 0.029 seconds)
