MULTILEVEL THRESHOLDING FOR MUTUAL INFORMATION BASED REGISTRATION AND IMAGE REGISTRATION USING A GPU
    1.
    发明申请
    MULTILEVEL THRESHOLDING FOR MUTUAL INFORMATION BASED REGISTRATION AND IMAGE REGISTRATION USING A GPU 有权
    使用GPU进行基于信息的注册和图像注册的多重阈值

    公开(公告)号:US20100027911A1

    公开(公告)日:2010-02-04

    申请号:US12509740

    申请日:2009-07-27

    IPC分类号: G06K9/32 G06T15/50

    摘要: An exemplary embodiment of the present invention includes a method of registering images. The method includes: for each image, determining an optimum intensity threshold set from a plurality of intensity threshold sets that maximizes a variance between classes of each set, segmenting each image using the corresponding determined optimum intensity threshold set, generating mutual information from a joint histogram of at least two of the segmented images, and registering the at least two images using the mutual information. The joint histogram may be generated using a geometry shader of a graphical processing unit.

    摘要翻译: 本发明的示例性实施例包括一种登记图像的方法。 该方法包括:对于每个图像,确定从多个强度阈值集合确定的最佳强度阈值集合,其使每组的类别之间的方差最大化,使用相应的确定的最佳强度阈值集分割每个图像,从联合直方图生成相互信息 的至少两个分割图像,以及使用所述相互信息登记所述至少两个图像。 联合直方图可以使用图形处理单元的几何着色器生成。

    Intensity-based image registration using Earth Mover's Distance
    2.
    发明申请
    Intensity-based image registration using Earth Mover's Distance 有权
    基于强度的图像注册,使用地球移动器的距离

    公开(公告)号:US20080039706A1

    公开(公告)日:2008-02-14

    申请号:US11805218

    申请日:2007-05-22

    IPC分类号: A61B5/05

    摘要: A method of aligning image having the steps of obtaining a first image, the first image having a corresponding first data set, obtaining a second image, the second having a corresponding second data set; learning a joint intensity distribution from a pair of prealigned images, and aligning the first image and the second image by computing Earth Mover's Distance between their observed joint intensity distribution and the learned joint intensity distribution.

    摘要翻译: 一种对准具有获得第一图像的步骤的图像的方法,所述第一图像具有对应的第一数据集,获得第二图像,所述第二图像具有对应的第二数据集; 从一对预对准图像学习联合强度分布,并通过计算地球移动器的观察到的关节强度分布与学习的关节强度分布之间的距离来对准第一图像和第二图像。

    Multilevel thresholding for mutual information based registration and image registration using a GPU
    3.
    发明授权
    Multilevel thresholding for mutual information based registration and image registration using a GPU 有权
    用于基于互信息的注册和使用GPU的图像注册的多级阈值

    公开(公告)号:US08731334B2

    公开(公告)日:2014-05-20

    申请号:US12509740

    申请日:2009-07-27

    IPC分类号: G06T1/20 G06T3/00 G06T7/00

    摘要: An exemplary embodiment of the present invention includes a method of registering images. The method includes: for each image, determining an optimum intensity threshold set from a plurality of intensity threshold sets that maximizes a variance between classes of each set, segmenting each image using the corresponding determined optimum intensity threshold set, generating mutual information from a joint histogram of at least two of the segmented images, and registering the at least two images using the mutual information. The joint histogram may be generated using a geometry shader of a graphical processing unit.

    摘要翻译: 本发明的示例性实施例包括一种登记图像的方法。 该方法包括:对于每个图像,确定从多个强度阈值集合确定的最佳强度阈值集合,其使每组的类别之间的方差最大化,使用相应的确定的最佳强度阈值集分割每个图像,从联合直方图生成相互信息 的至少两个分割图像,以及使用所述相互信息登记所述至少两个图像。 联合直方图可以使用图形处理单元的几何着色器生成。

    Intensity-based image registration using Earth Mover's Distance
    4.
    发明授权
    Intensity-based image registration using Earth Mover's Distance 有权
    基于强度的图像注册,使用地球移动器的距离

    公开(公告)号:US08121379B2

    公开(公告)日:2012-02-21

    申请号:US11805218

    申请日:2007-05-22

    IPC分类号: G06K9/00

    摘要: A method of aligning image having the steps of obtaining a first image, the first image having a corresponding first data set, obtaining a second image, the second having a corresponding second data set; learning a joint intensity distribution from a pair of prealigned images, and aligning the first image and the second image by computing Earth Mover's Distance between their observed joint intensity distribution and the learned joint intensity distribution.

    摘要翻译: 一种对准具有获得第一图像的步骤的图像的方法,所述第一图像具有对应的第一数据集,获得第二图像,所述第二图像具有对应的第二数据集; 从一对预对准图像学习联合强度分布,并通过计算地球移动器的观察到的关节强度分布与学习的关节强度分布之间的距离来对准第一图像和第二图像。