Method and apparatus for reconstructing a three-dimensional image volume from two-dimensional projection images
    1.
    发明授权
    Method and apparatus for reconstructing a three-dimensional image volume from two-dimensional projection images 有权
    用于从二维投影图像重建三维图像体积的方法和装置

    公开(公告)号:US07728834B2

    公开(公告)日:2010-06-01

    申请号:US11523394

    申请日:2006-09-19

    IPC分类号: G06T17/00 A61B6/00

    CPC分类号: G06T11/006 G06T11/005

    摘要: The invention relates to a method and an apparatus for reconstructing a three-dimensional image volume from two-dimensional projection images of a subject which have been taken from different projection directions by rotating the recording system around the subject, wherein the grayscale values of the voxels of the image volume are calculated by back projection of the projection images. The invention is characterized in that prior to back projection at least one projection image is modified in such a way that it corresponds to a projection image taken with a virtual detector whose axes are aligned parallel to the rotational axis of the recording system.

    摘要翻译: 本发明涉及一种用于通过使记录系统围绕被摄体旋转而从不同投影方向拍摄的被摄物体的二维投影图像重建三维图像体积的方法和装置,其中,体素的灰度值 通过投影图像的反投影来计算图像体积。 本发明的特征在于,在背投之前,至少一个投影图像被修改为使得其对应于用虚拟检测器拍摄的投影图像,虚拟检测器的轴线平行于记录系统的旋转轴线排列。

    Drive mechanism for a timepiece calendar date display
    2.
    发明授权
    Drive mechanism for a timepiece calendar date display 有权
    钟表日历日期显示的驱动机构

    公开(公告)号:US07839724B2

    公开(公告)日:2010-11-23

    申请号:US12092606

    申请日:2006-12-05

    IPC分类号: G04B19/24

    CPC分类号: G04B19/25386

    摘要: A calendar date display comprises a ten-day indicator (2) and a unit indicator (1) driven by a program drive (8), which is provided with a calendar date display (9) whose toothing is engaged with the beak (15) of a lever (16) in such a way that a wheel is moved one step forward by one date number change. Between each calendar number change, the beak (15) is engaged between the first and second teeth (11, 12) of the wheel (9). At the time of the calendar number change, the beak (15) is disengaged from said first and second teeth (11, 12) in such a way that it is engaged between the second and third (12, 13) teeth of the wheel (9), thereby moving said wheel one step forward.

    摘要翻译: 日历日期显示包括由程序驱动器(8)驱动的十天指示器(2)和单元指示器(1),该单元指示器设置有其齿与喙(15)接合的日历日期显示(9) 杠杆(16)的方式使得车轮向前移动一个日期数字变化。 在每个日历数变化之间,喙(15)接合在车轮(9)的第一和第二齿(11,12)之间。 在日历编号改变时,喙(15)与所述第一和第二齿(11,12)分离,使得其接合在车轮的第二和第三(12,13)齿之间 9),从而使所述车轮向前移动一步。

    Method and arrangement for pattern recognition on the basis of statistics
    3.
    发明授权
    Method and arrangement for pattern recognition on the basis of statistics 失效
    在统计的基础上进行模式识别的方法和布置

    公开(公告)号:US06205247B1

    公开(公告)日:2001-03-20

    申请号:US09202027

    申请日:1998-12-08

    IPC分类号: G06K962

    CPC分类号: G06K9/6281 G06K9/6287

    摘要: A method and an arrangement are presented for pattern recognition on the basis of statistics. According to the method, for an object to be recognized on the basis of a complete set of two-class or multiclass classifiers, the association with each target class of the class set is estimated with a numerical value that is produced by cascaded use of polynomial classifiers. According to the invention, on a learning sample in which all class patterns to be recognized are sufficiently represented, there is a selection, from all the two-class or multiclass classifiers by way of their estimation vector spectrum, of those two-class or multiclass classifiers with estimations contributing the most to minimize a scalar quantity calculated over the estimation vector spectrum and having high separating relevance. The selected two-class or multiclass classifiers are subsequently used to form, via an expanded learning sample, estimation vectors from which expanded characteristic vectors are produced by polynomial linking. An evaluation classifier is formed on the basis of said characteristic vectors for estimating all target classes.

    摘要翻译: 提出了一种基于统计学模式识别的方法和方案。 根据该方法,对于基于两类或多类分类器的完整集合来识别的对象,使用通过级联使用多项式产生的数值来估计与集合的每个目标类别的关联 分类器 根据本发明,在所有要被识别的类别模式被充分表示的学习样本中,从所有两类或多类分类器中通过它们的估计向量谱来选择那些两类或多类 具有估计的分类器最有助于最小化在估计向量谱上计算的具有高分离相关性的标量。 所选择的两类或多类分类器随后用于经由扩展学习样本形成通过多项式链接从其产生扩展特征向量的估计向量。 基于用于估计所有目标等级的所述特征向量形成评估分类器。