-
公开(公告)号：KR1020140067526A
公开(公告)日：2014-06-05
申请号：KR1020120134868
申请日：2012-11-26
Applicant: 삼성전자주식회사
IPC: G06T17/10
CPC classification number: A61B6/5264 , A61B6/12 , G06T7/38 , G06T2200/04 , G06T2207/10084 , G06T2207/30004
Abstract: Disclosed is a method for matching medical images. The method for matching medical images according to an embodiment of the present invention comprises the steps of acquiring a first medical image photographed by a first medical device for a first cross section selected within a volume of interest (VOI); detecting a cross-sectional image corresponding to the first cross section from a set of second medical images previously photographed for the VOI based on anatomical features shown in the first medical image; mapping virtual coordinate systems used by the first medical device and the second medical device which photographs the second medical images, based on the detected cross-sectional image and the first medical image; and tracking the movement of the cross section, which is photographed by the first medical device, on the set of the second medical images using the mapped virtual coordinate systems.
Abstract translation: 公开了一种用于匹配医学图像的方法。 根据本发明的实施例的用于匹配医学图像的方法包括以下步骤：获取由第一医疗设备拍摄的用于在感兴趣体积（VOI）内选择的第一横截面的第一医疗图像; 基于第一医学图像中所示的解剖特征，从先前针对VOI拍摄的第二医疗图像的集合检测对应于第一横截面的横截面图像; 基于检测到的横截面图像和第一医学图像，映射由第一医疗装置和第二医疗装置使用的虚拟坐标系，所述第二医疗装置拍摄第二医疗图像; 以及使用映射的虚拟坐标系来跟踪由第一医疗设备拍摄的横截面的运动在第二医疗图像的集合上。
-
公开(公告)号：KR1020140032810A
公开(公告)日：2014-03-17
申请号：KR1020120099548
申请日：2012-09-07
CPC classification number: G06T7/0016 , G06T7/33 , G06T2207/10081 , G06T2207/10084 , G06T2207/10088 , G06T2207/10104 , G06T2207/10136 , G06T2207/30056 , G06T2207/30084 , G06T2207/30101
Abstract: A method for matching a plurality of medical images is disclosed. The medical image matching method according to an embodiment of the present invention comprises: obtaining a first medical image taken before a medical procedure and a second medical image taken in real-time during the medical procedure; extracting feature points for each of at least two adjacent entities, which are identifiable in the second medical image having a low resolution, from the first medical image and the second medical image among a plurality of anatomical entities adjacent to an organ of interest of a patient; and matching the first medical image and the second medical image based on a geometrical relationship between the adjacent objects displayed by the feature points of the first medical image and a geometrical relationship between the adjacent objects displayed by the feature points of the second medical image. [Reference numerals] (210) First medical image storage unit; (220) Second medical image storage unit; (230) Feature point extracting unit; (231) Adjacent objects extracting unit; (232) Coordinate extracting unit; (240) Matching unit; (241) Vector calculating unit; (242) Matrix calculating unit; (243) Basic matching unit; (244) Boundary area selecting unit; (245) Matching image correcting unit; (AA) First medical image; (BB) Second medical image; (CC) Image process processor
Abstract translation: 公开了一种用于匹配多个医学图像的方法。 根据本发明的实施例的医学图像匹配方法包括：获得在医疗过程之前拍摄的第一医疗图像和在医疗过程中实时拍摄的第二医疗图像; 从与患者感兴趣的器官相邻的多个解剖实体中的第一医学图像和第二医疗图像提取至少两个相邻实体中的每一个的特征点，其可以在具有低分辨率的第二医学图像中被识别 ; 并且基于由第一医学图像的特征点显示的相邻对象之间的几何关系和由第二医学图像的特征点显示的相邻对象之间的几何关系，匹配第一医疗图像和第二医疗图像。 （附图标记）（210）第一医用图像存储单元; （220）第二医用图像存储单元; （230）特征点提取单元; （231）相邻对象提取单元; （232）坐标提取单元; （240）配套单元; （241）向量计算单元; （242）矩阵计算单元; （243）基本匹配单位; （244）边界区选择单位; （245）匹配图像校正单元; （AA）第一医学图像; （BB）第二医学图像; （CC）图像处理处理器
-
公开(公告)号：KR1020130143434A
公开(公告)日：2013-12-31
申请号：KR1020120066991
申请日：2012-06-21
Applicant: 삼성전자주식회사
CPC classification number: A61B34/10 , A61B2017/00699 , A61B2034/105 , A61B2090/364 , A61B2090/378 , A61N7/02
Abstract: A method for determining focus of high-intensity focused ultrasound (HIFU), which is changed by body activities, comprises the steps of: designating location of an observation point, which is a datum point for transmission and reception of ultrasound, to a three-dimensional organ model which shows anatomical information of the organ; obtaining first location, in which the observation point is moved, by the morphological change of the three-dimensional organ model; transmitting the ultrasound to the observation point and obtaining displacement of the observation point using time to receive reflected wave; obtaining second location, in which the observation point is moved, using the obtained displacement; determining location, in which the observation point is moved, based on the first and second location; and determining focus of the high-intensity focused ultrasound based on the determined location of the observation point. [Reference numerals] (10) Focus deciding device;(100) Ultrasound therapy device;(30) Image sensing device;(40) High strength connection ultrasonic device;(50) Medical image generation device
Abstract translation: 一种用于确定由身体活动改变的高强度聚焦超声（HIFU）的焦点的方法包括以下步骤：将作为超声波发射和接收的基准点的观察点的位置指定到三维 显示器官的解剖信息的三维器官模型; 通过三维器官模型的形态学变化获得观察点移动的第一个位置; 将超声波传输到观察点，并使用时间获得观察点的位移以接收反射波; 使用获得的位移获得其中观察点移动的第二位置; 基于第一和第二位置确定观察点被移动的位置; 以及基于确定的观察点的位置来确定高强度聚焦超声的焦点。 （10）聚焦判定装置（100）超声波治疗装置（30）图像感知装置;（40）高强度连接超声波装置;（50）医疗图像生成装置
-
公开(公告)号：KR101303877B1
公开(公告)日：2013-09-04
申请号：KR1020050071887
申请日：2005-08-05
Applicant: 삼성전자주식회사
IPC: G06T7/40
CPC classification number: G06K9/00234 , G06T7/11 , G06T2207/20132
Abstract: 본 발명은 얼굴 검출과 피부 영역 검출을 적용하여 피부의 선호색 변환을 수행하는 방법 및 장치에 관한 발명으로서 본 발명의 일 실시예에 따른 얼굴 검출과 피부 영역 검출을 적용하여 피부의 선호색 변환을 수행하는 방법은 입력된 영상에서 얼굴 영역을 검출하는 단계, 상기 입력된 영상에서 피부 영역을 검출하는 단계, 상기 얼굴 영역과 상기 피부 영역의 공통 영역을 얼굴로 판단하는 단계, 상기 판단하는 단계에서 판단한 얼굴에 존재하는 피부색을 참조하여 상기 입력된 영상에서 피부색을 추출하는 단계, 및 상기 추출한 피부색을 영상 적응적 피부색으로 변환하는 단계를 포함한다.
영상, 피부색, 얼굴 검출, 피부 영역 검출, 색상 변환Abstract translation: 公开了一种通过应用面部检测和皮肤颜色检测来将输入图像的肤色转换成偏好颜色的方法和装置。 该方法包括：从输入图像中检测面部区域; 从所述输入图像检测皮肤区域; 判断面部和皮肤区域之间的共同区域作为面部; 参照所述判断面部的肤色，从所述输入图像提取肤色; 并将所提取的肤色转换为图像适应肤色。
-
公开(公告)号：KR1020130026041A
公开(公告)日：2013-03-13
申请号：KR1020110089388
申请日：2011-09-05
Applicant: 삼성전자주식회사
CPC classification number: G06T7/75 , G06T17/00 , G06T19/00 , G06T2207/10072 , G06T2207/10116 , G06T2207/10132 , G06T2207/20056 , G06T2207/20096 , G06T2207/30056 , G06T2207/30096 , G06T2210/41
Abstract: PURPOSE: A method and an apparatus for producing a medical image using a partial medical image are provided to easily find the position of an organ. CONSTITUTION: An organ image system includes an image detecting device(10), an image registration apparatus(20) and an image display device(30). A probe(11) is mounted on the image detecting device. A source signal generated from the probe is delivered to the specific part of the patient body. An image detecting device detects a three dimensional image by using ultrasound. [Reference numerals] (AA) Patient
Abstract translation: 目的：提供一种使用部分医用图像生成医用图像的方法和装置，以容易地找到器官的位置。 构成：器官图像系统包括图像检测装置（10），图像登记装置（20）和图像显示装置（30）。 探头（11）安装在图像检测装置上。 从探针产生的源信号被传送到患者身体的特定部分。 图像检测装置通过使用超声波检测三维图像。 （附图标记）（AA）患者
-
Patent Agency Ranking
公开(公告)号：KR101195613B1
公开(公告)日：2012-10-29
申请号：KR1020060073770
申请日：2006-08-04
Applicant: 삼성전자주식회사
IPC: H04N5/93
Abstract: 동영상의 주제별 분할장치 및 방법이 개시된다. 동영상의 주제별 분할장치는 복수의 프레임으로 구성되는 비디오 시퀀스에서 인물 정보를 이용하여 복수의 키 프레임을 검출하고, 검출된 키프레임들을 각 주제의 시작 샷으로 결정하는 시작 샷 결정부; 및 상기 각 주제의 시작 샷을 이용하여 주제 리스트를 생성하는 주제 리스트 생성부로 이루어진다.
영상, 주제, 분할, 인물-
公开(公告)号：KR1020120077105A
公开(公告)日：2012-07-10
申请号：KR1020100138939
申请日：2010-12-30
Applicant: 삼성전자주식회사
CPC classification number: G01B11/14 , G01J1/4257 , G01S3/783 , G01S5/16 , G01S11/06 , G06F3/0304 , G01J1/28
Abstract: PURPOSE: A system and a method for sensing high accuracy signals using the infrared rays are provided to selectively use an intensity difference between received lights or light receiving intensity, thereby preciously measuring a signal to noise ratio with high signals for estimating a light emitting device. CONSTITUTION: A system(100) for sensing high accuracy signals using the infrared rays comprises a receiver and a measurement device(120). The receiver receives signals from a projectile. The measurement device measures the intensity of each first and second signal according to a distance and a receiving direction. The measurement device measures signals per each oriented direction for estimating an object including the projectile by using at least one between the measured intensity and the intensity difference. The measurement device measures the signals corresponding to the intensity difference as the signals per each oriented direction in the oriented direction where first intensity measured with respect to the first signal or second intensity measured with respect to the second signal is smaller than the intensity difference.
Abstract translation: 目的：提供一种用于使用红外线检测高精度信号的系统和方法，以选择性地使用接收光或光接收强度之间的强度差，从而通过用于估计发光器件的高信号珍贵地测量信噪比。 构成：用于使用红外线感测高精度信号的系统（100）包括接收器和测量装置（120）。 接收器接收来自射弹的信号。 测量装置根据距离和接收方向测量每个第一和第二信号的强度。 测量装置通过使用测量强度和强度差之间的至少一个来测量每个取向方向上的信号，以估计包括射弹的物体。 测量装置测量对应于强度差的信号作为在相对于第二信号测量的第一信号或第二强度测量的第一强度的第一强度小于强度差的朝向方向上的每个取向方向的信号。
-
公开(公告)号：KR1020120066767A
公开(公告)日：2012-06-25
申请号：KR1020100128028
申请日：2010-12-15
Applicant: 삼성전자주식회사
CPC classification number: F25D25/005 , F25D2323/021
Abstract: PURPOSE: A storage container and a refrigerator having the same are provided to prevent overcooling of food storing in a storage container by preventing rapid temperature change of the storage container, and to freshly preserve the food storing in the storage container for a long time by smoothly transferring cool air to the storage container. CONSTITUTION: A refrigerator comprises a main body, storage chambers, partitions, and storage containers(210). Each storage container comprises a container body, a thickness reinforcing unit, and an insulating member. The container body forms an outer shape of the storage container and is upwardly opened. In order to prevent rapid temperature change in the lower part of the container body by cool air of the storage chamber, the thickness reinforcing unit is formed in the lower part of the container body. The insulating member is arranged in a space between the thickness reinforcing unit and the container body.
Abstract translation: 目的：提供储存容器和具有该容器的冰箱，以通过防止储存容器的快速温度变化来防止储存容器中的食物过度冷却，并且通过平稳地将食物储存在储存容器中长时间地保存 将冷空气转移到储存容器。 构成：冰箱包括主体，储存室，隔板和储存容器（210）。 每个储存容器包括容器主体，厚度增强单元和绝缘构件。 容器主体形成存储容器的外形并向上打开。 为了防止储存室的冷空气对容器主体的下部进行快速的温度变化，厚度增强单元形成在容器主体的下部。 绝缘构件设置在厚度增强单元和容器主体之间的空间中。
-
公开(公告)号：KR1020090040209A
公开(公告)日：2009-04-23
申请号：KR1020080084039
申请日：2008-08-27
Applicant: 삼성전자주식회사
CPC classification number: G06K9/00275 , G06K9/6234
Abstract: A multi-view face recognition method and a system thereof are provided to reduce an amount of calculation for face recognition and to meet various demanded conditions in face recognition field by determining an identity of two inputted images based on a distance between two feature vectors. An eye position determining unit(120) searches a position of eyes in inputted images by face detecting unit(110), and calculates the coordinate of the two eyes. A feature extracting unit(140) extracts feature vectors from two face images based on a linear projection matrix provided from a face recognition engine learning unit(150), and inputs the extracted feature vectors to a vector distance calculating unit(160). The vector distance calculating unit calculates a distance between the feature vector of one face image and the feature vector of the other face image. A determining unit(170) measures the distance of the vectors based on a predetermined threshold, and determines whether the images to be recognized are identical person or not.
Abstract translation: 提供一种多视角人脸识别方法及其系统，以便通过基于两个特征向量之间的距离来确定两个输入图像的身份来减少面部识别的计算量并满足人脸识别领域中的各种要求条件。 眼睛位置确定单元（120）通过面部检测单元（110）搜索输入图像中的眼睛的位置，并且计算两只眼睛的坐标。 特征提取单元（140）基于从面部识别引擎学习单元（150）提供的线性投影矩阵从两个脸部图像中提取特征向量，并将所提取的特征向量输入到矢量距离计算单元（160）。 矢量距离计算单元计算一个面部图像的特征向量与另一个面部图像的特征向量之间的距离。 确定单元（170）基于预定阈值来测量向量的距离，并且确定要识别的图像是否是相同的人。
-
公开(公告)号：KR1020070117393A
公开(公告)日：2007-12-12
申请号：KR1020060051611
申请日：2006-06-08
Applicant: 삼성전자주식회사
CPC classification number: G06K9/6209
Abstract: A method for extracting the image of an object from a digital image using prior shape information and a system for performing the method are provided to employ a weight model expressing a weight map as prior shape information to extract the specific region more smoothly. Image information is synthesized with shape information based on the input image and prior shape information. A specific area is extracted from the input image through the image information. The prior shape information includes a shape model and a weight model. The image information is synthesized with the shape information based on the input image and the prior shape information. Shape constraint is created based on the input image and the shape model(S411). A shape-based gradient image is created based on a similar shape and a gradient image(S412). A shape-based weight value image is created by the input image, the tri-map of the input image and the weight model(S413).
Abstract translation: 提供一种使用先前形状信息从数字图像提取对象的图像的方法和用于执行该方法的系统，以使用表示权重映射的权重模型作为先前的形状信息，以更平滑地提取特定区域。 基于输入图像和先前形状信息的形状信息合成图像信息。 通过图像信息从输入图像提取特定区域。 先前的形状信息包括形状模型和权重模型。 图像信息与基于输入图像和先前形状信息的形状信息合成。 基于输入图像和形状模型创建形状约束（S411）。 基于类似形状和梯度图像创建基于形状的渐变图像（S412）。 通过输入图像，输入图像的三维图和权重模型创建基于形状的权重值图像（S413）。
-
-
-
-
-
-
-
-
-
Search Results
195
records
(took 0.038 seconds)
