利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

86 条记录 (耗时 0.03 秒)

    Statistical model
    13.
    发明申请
    Statistical model 有权
    统计模型

    公开(公告)号：US20050027492A1

    公开(公告)日：2005-02-03

    申请号：US10480445

    申请日：2001-12-06

    申请人： Christopher Taylor ,  Rhodi Davies ,  Timothy Cootes ,  Carole Twining

    发明人： Christopher Taylor ,  Rhodi Davies ,  Timothy Cootes ,  Carole Twining

    IPC分类号： G06K9/48 ,  G06K9/62 ,  G06F17/10

    CPC分类号： G06K9/48 ,  G06K9/6214 ,  G06K9/6255 ,  G06K2009/484

    摘要： A method of building a statistical shape model by automatically establishing correspondence between a set of two dimensional shapes or three dimensional shapes, the method comprising: a) determining a parameterisation of each shape, building a statistical shape model using the parameterisation, using an objective function to provide an output which indicates the quality of the statistical shape model; performing step a) repeatedly for different parameterisations and comparing the quality of the resulting statistical shape models using output of the objective function to determine which parameterisation provides the statistical shape model having the best quality, wherein the output of the objective function is a measure of the quantity of information required to code the set of shapes using the statistical shape model.

    摘要翻译： 一种通过自动建立一组二维形状或三维形状之间的对应关系来建立统计形状模型的方法，所述方法包括：a）确定每个形状的参数化，使用参数化建立统计形状模型，使用目标函数 提供指示统计形状模型的质量的输出; 对于不同的参数重复执行步骤a），并使用目标函数的输出来比较所得到的统计形状模型的质量，以确定哪个参数化提供具有最佳质量的统计形状模型，其中目标函数的输出是 使用统计形状模型编码形状集所需的信息量。

    Method of describing object region data, apparatus for generating object region data, video processing apparatus and video processing method
    14.
    发明授权
    Method of describing object region data, apparatus for generating object region data, video processing apparatus and video processing method 失效
    描述对象区域数据的方法，用于生成对象区域数据的装置，视频处理装置和视频处理方法

    公开(公告)号：US06810148B2

    公开(公告)日：2004-10-26

    申请号：US10278938

    申请日：2002-10-24

    申请人： Toshimitsu Kaneko ,  Osamu Hori ,  Takeshi Mita ,  Koji Yamamoto

    发明人： Toshimitsu Kaneko ,  Osamu Hori ,  Takeshi Mita ,  Koji Yamamoto

    IPC分类号： G06K900

    CPC分类号： G06K9/48 ,  G06K9/6204 ,  G06K2009/484 ,  G06T7/251 ,  G06T2207/10016 ,  H04N19/20 ,  H04N19/54 ,  H04N19/543 ,  H04N19/70

    摘要： A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the region, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

    摘要翻译： 一种用于在多个帧中描述关于视频中的任意对象的区域的区域数据的区域数据描述方法，所述方法使用近似该区域或特征点的近似图形来指定视频中的对象区域 近似通过将代表点的位置数据或特征点在帧进行预定功能的方向上并将该功能的参数描述为区域数据而获得的轨迹。 因此，可以用少量的数据来描述视频中的预定对象的区域。 此外，可以容易地执行数据的创建和处理。

    METHOD AND SYSTEM FOR DETECTION OF BONE STRUCTURE
    18.
    发明申请
    METHOD AND SYSTEM FOR DETECTION OF BONE STRUCTURE 有权
    用于检测骨结构的方法和系统

    公开(公告)号：US20160302748A1

    公开(公告)日：2016-10-20

    申请号：US14947560

    申请日：2015-11-20

    申请人： National Applied Research Laboratories

    发明人： Wei-Jeng CHANG ,  Chia-Yang SUN ,  Charlie H. CHANG ,  Huang-Wen HUANG ,  Po-Ying LI ,  Ching-I HSIEH ,  Cheng-Wei KU ,  Kuen-Long TASI

    IPC分类号： A61B6/00 ,  G06K9/48 ,  G06T11/00 ,  G06K9/46 ,  A61B6/03 ,  G06T7/00

    CPC分类号： A61B6/505 ,  A61B6/032 ,  A61B6/5217 ,  G06K9/481 ,  G06K2009/484 ,  G06K2209/055 ,  G06T7/0012 ,  G06T7/60 ,  G06T2207/10081 ,  G06T2207/30008

    摘要： The present invention provides a method and system for detection of bone structure, the method executing operation process and image reconstruction according to an image of a skeleton captured by CT scanner, to present distributed state of a bone structural parameter of the skeleton for diagnosing. The method comprises allocating at least one bone from the image of the skeleton to be analyzed, wherein the image of the bone is composed by pixels, and each pixel includes luminance value positively relating to the bone structural parameter; aligning a major axis of inertia principal axis of the bone to a principal axis of Cartesian coordinate; a cortical bone area of the bone intersecting at least one principal plane which is perpendicular to the principal axis, and each principal plane forming an outer contour line and an inner contour line of the cortical bone area; processing a analytic algorithm for the bone structural parameter, in the inner area of the outer contour line in the principal plane, to perform distributed state of the bone structural parameter along the outer contour line; calculating distributed state of the bone structural parameter along the outer contour line in each principal plane, to perform distributed state of the bone structural parameter of the bone; performing distributed state of the bone structural parameter of the bone by assembling distributed state of the bone structural parameter over the outer contour line of each principal plane, and performing distributed state of the bone structural parameter of the skeleton by assembling distributed state of the bone structural parameter of each bone.

    摘要翻译： 本发明提供一种根据CT扫描仪拍摄的骨架图像执行骨结构的方法和系统，该方法执行操作过程和图像重建，以呈现用于诊断的骨架的骨结构参数的分布状态。 该方法包括从要分析的骨架的图像中分配至少一个骨骼，其中骨骼的图像由像素组成，并且每个像素包括与骨结构参数正相关的亮度值; 将骨的惯性主轴的主轴对准笛卡尔坐标的主轴; 所述骨的皮质骨区域与垂直于所述主轴线的至少一个主平面相交，并且每个主平面形成所述皮质骨区域的外轮廓线和内轮廓线; 在主平面内的外轮廓线的内部区域处理骨结构参数的分析算法，沿外轮廓线执行骨结构参数的分布状态; 计算骨骼结构参数沿着每个主平面中的外轮廓线的分布状态，以实现骨骼骨结构参数的分布状态; 通过在每个主平面的外轮廓线上组装骨结构参数的分布状态来执行骨的骨结构参数的分布状态，并且通过组装骨结构的分布状态来执行骨骼的骨结构参数的分布状态 每个骨骼的参数。