公开(公告)号：US06370270B1

公开(公告)日：2002-04-09

申请号：US09385121

申请日：1999-08-27

Applicant: Dinesh Nair ,  Lothar Wenzel ,  Nicolas Vazquez ,  Samson DeKey

Inventor： Dinesh Nair ,  Lothar Wenzel ,  Nicolas Vazquez ,  Samson DeKey

IPC: G06K962

CPC classification number: G06K9/6203 ,  G06K2209/19 ,  G06T7/223 ,  G06T7/248 ,  G06T7/74 ,  G06T2207/10016 ,  G06T2207/30108

Abstract: A system and method for improved image characterization, object placement, and mesh design utilizing Low Discrepancy sequences. The Low Discrepancy sequence is designed to produce sample points which maximally avoid one another, i.e., the distance between any two sample points is maximized. The invention may be applied specifically to methods of image characterization, pattern matching, acquiring image statistics, object location, image reconstruction, motion estimation, object placement, sensor placement, and mesh design, among others. Image characterization is performed by receiving an image and then sampling the image using a Low Discrepancy sequence, also referred to as a quasi-random sequence, to determine a plurality of sample pixels in the image which characterize the image. Sensor placement is performed by generating a Low Discrepancy sequence for the desired placement application, and then selecting locations for the optimal placement of sensors using the generated Low Discrepancy sequence.

Abstract translation: 一种利用低差异序列改进图像表征，物体放置和网格设计的系统和方法。 低偏差序列被设计为产生最大程度地相互避免的采样点，即，任何两个采样点之间的距离最大化。 本发明可以专门应用于图像表征，模式匹配，获取图像统计，对象位置，图像重建，运动估计，对象放置，传感器放置和网格设计等的方法。 通过接收图像并且然后使用低差异序列（也称为准随机序列）对图像进行采样来确定图像中表征图像的多个样本像素来执行图像表征。 通过为所需的放置应用生成低差分序列，然后使用生成的低差异序列选择位置以实现传感器的最佳放置来执行传感器放置。

公开(公告)号：US07158677B2

公开(公告)日：2007-01-02

申请号：US10224043

申请日：2002-08-20

Applicant: Lothar Wenzel ,  Ram Rajagopal ,  Dinesh Nair

Inventor： Lothar Wenzel ,  Ram Rajagopal ,  Dinesh Nair

IPC: G06K9/46

CPC classification number: G06K9/6204

Abstract: System and method for determining the presence of an object of interest from a template image in an acquired target image, despite of or using various types of affine transformations of the object of interest in the target image. A template image discrete curve is determined from the template image corresponding to the object of interest, and a template curve canonical transform calculated based on the curve. The canonical transform is applied to the template curve to generate a mapped template curve. The target image is received, a target image discrete curve determined, and a target curve canonical transform computed based on the target curve canonical transform. The target canonical transform is applied to the target curve to generate a mapped target curve. Geometric pattern matching is performed using the mapped template and target image discrete curves to generate pattern matching results, and the pattern matching results are output.

Abstract translation: 尽管在目标图像中使用或使用感兴趣对象的各种仿射变换来确定所获取的目标图像中的模板图像中感兴趣对象的存在的系统和方法。 从与感兴趣对象相对应的模板图像确定模板图像离散曲线，并根据曲线计算模板曲线规范变换。 将规范变换应用于模板曲线以生成映射的模板曲线。 接收目标图像，确定目标图像离散曲线，并且基于目标曲线规范变换计算的目标曲线规范变换。 将目标规范变换应用于目标曲线以生成映射的目标曲线。 使用映射的模板和目标图像离散曲线进行几何模式匹配，以生成模式匹配结果，并输出模式匹配结果。

公开(公告)号：US07139432B2

公开(公告)日：2006-11-21

申请号：US10264118

申请日：2002-10-03

Applicant: Lothar Wenzel ,  Ram Rajagopal ,  Satish V. Kumar ,  Darren R. Schmidt ,  Kevin M. Crotty ,  Matthew S. Fisher ,  Dinesh Nair

Inventor： Lothar Wenzel ,  Ram Rajagopal ,  Satish V. Kumar ,  Darren R. Schmidt ,  Kevin M. Crotty ,  Matthew S. Fisher ,  Dinesh Nair

IPC: G06K9/00

CPC classification number: G06K9/6204 ,  G06K9/48 ,  G06K9/6203

Abstract: System and method for determining the presence of an object of interest in a target image. Regions of a target image may be located that match an object of interest, e.g., in a template image, with respect to various information, e.g., luminance, color and/or other types of boundary information. The invention includes improved methods for mapping point sequences (e.g., pixel sequences) or curves to new point sets or curves for curve matching. The method determines the presence of an object of interest in a target image despite of or using various types of topological transformations of the object of interest in the target image. One or more mapping operators are determined based on template curves and/or example target curves. Pattern matching is performed on one or more target images using the mapping operator(s) to generate pattern matching results, and the pattern matching results output.

公开(公告)号：US07120301B2

公开(公告)日：2006-10-10

申请号：US10264109

申请日：2002-10-03

Applicant: Lothar Wenzel ,  Ram Rajagopal ,  Satish V. Kumar ,  Darren R. Schmidt ,  Kevin M. Crotty ,  Matthew S. Fisher ,  Dinesh Nair

Inventor： Lothar Wenzel ,  Ram Rajagopal ,  Satish V. Kumar ,  Darren R. Schmidt ,  Kevin M. Crotty ,  Matthew S. Fisher ,  Dinesh Nair

IPC: G06K9/62

CPC classification number: G06K9/6204 ,  G06K9/48

Abstract: System and method for re-sampling discrete curves, thereby efficiently characterizing point sets or curves in a space. The method may also provide improved means for mapping point sets or curves to new point sets or curves for curve matching. A weight vector or function is determined based on a plurality of discrete curves, e.g., from one or more template data sets or images. The weight function enhances differences between weighted discrete curves. A set of orthonormal polynomials is determined based on the computed weight function, where the set of orthonormal polynomials comprises a set of orthogonal eigenfunctions of a Sturm-Liouville differential equation. Values for a plurality of zeros for one of the set of orthonormal polynomials is determined that comprise resampling points for the plurality of discrete curves. Each of the plurality of discrete curves is resampled based on the determined values of the plurality of zeros.

公开(公告)号：US07034831B2

公开(公告)日：2006-04-25

申请号：US09876977

申请日：2001-06-08

Applicant: Lothar Wenzel ,  Ram Rajagopal ,  Dinesh Nair

Inventor： Lothar Wenzel ,  Ram Rajagopal ,  Dinesh Nair

IPC: G06T11/20

CPC classification number: G06Q10/047 ,  G05B19/00 ,  G05B19/41815 ,  G05B2219/32212 ,  G05B2219/40554 ,  G06F17/10 ,  G06K9/20 ,  G06K9/50 ,  G06K9/52 ,  G06T7/0004 ,  Y02P90/08 ,  Y02P90/22

Abstract: A system and method for generating a curve in a region, e.g., a Low Discrepancy Curve. The method may generate an unbounded Low Discrepancy Point (LDP); apply one or more boundary conditions to the unbounded LDP to generate a bounded LDP located within the region; repeat said generating and said applying one or more boundary conditions one or more times, generating a Low Discrepancy Sequence (LDS) in the region; store the LDS; and generate output comprising the LDS, wherein the LDS defines the curve in the region. The method may scan the region according to the defined curve. In generating the unbounded LDP, the method may select two or more irrational numbers, a step size epsilon (ε), and a starting position; initialize a current position to the starting position; and increment components of the current position based on ε and the irrational numbers to generate the unbounded LDP.

Abstract translation: 用于在区域中产生曲线的系统和方法，例如低差异曲线。 该方法可以产生无界低差异点（LDP）; 对无界LDP应用一个或多个边界条件，以产生位于该区域内的有界LDP; 重复所述生成并且表示施加一个或多个边界条件一次或多次，在该区域中产生低差异序列（LDS）; 存储LDS; 并且生成包括LDS的输出，其中LDS定义该区域中的曲线。 该方法可以根据定义的曲线扫描该区域。 在生成无界LDP时，该方法可以选择两个或更多个无理数，步长ε（ε）和开始位置; 将当前位置初始化为起始位置; 并且基于ε和不合理数增加当前位置的分量以生成无界LDP。

公开(公告)号：US06909801B2

公开(公告)日：2005-06-21

申请号：US09876982

申请日：2001-06-08

Applicant: Lothar Wenzel ,  Ram Rajagopal ,  Dinesh Nair

Inventor： Lothar Wenzel ,  Ram Rajagopal ,  Dinesh Nair

IPC: G05B19/418 ,  G06F17/10 ,  G06K9/20 ,  G06K9/50 ,  G06K9/52 ,  G06Q10/04 ,  G06T7/00 ,  G06R9/00

CPC classification number: G06T7/0004 ,  G05B19/41815 ,  G05B2219/32212 ,  G05B2219/40554 ,  G06F17/10 ,  G06K9/20 ,  G06K9/50 ,  G06K9/52 ,  G06Q10/047 ,  Y02P90/08 ,  Y02P90/12 ,  Y02P90/22

Abstract: A system and method for generating a curve, such as a Low Discrepancy Curve, on a surface, such as an abstract surface with a Riemannian metric. The system may comprise a computer which includes a CPU and a memory medium which is operable to store one or more programs executable by the CPU to perform the method. The method may: 1) parameterize the surface; 2) select a curve, such as a Low Discrepancy Curve, in a parameter space, for example, a simple space such as a unit square; 3) re-parameterize the surface, for example, re-parameterize the surface such that a ratio of line and area elements of the surface based on a Riemannian metric is constant; and 4) map the curve onto the surface using the re-parameterization. The method may also generate output comprising information regarding the mapped curve, for example, displaying the mapped curve on a display device.

Abstract translation: 用于在诸如具有黎曼度量的抽象表面的表面上生成诸如低差异曲线的曲线的系统和方法。 该系统可以包括计算机，其包括CPU和存储介质，该存储介质可操作以存储由CPU执行的一个或多个程序以执行该方法。 该方法可以：1）参数化表面; 2）在参数空间中选择一个曲线，例如低偏差曲线，例如单位平方的简单空间; 3）重新参数化表面，例如，重新参数化表面，使得基于黎曼度量的表面的线和面积元素的比率是恒定的; 和4）使用重新参数化将曲线映射到曲面上。 该方法还可以生成包括关于映射曲线的信息的输出，例如，在显示设备上显示映射曲线。

公开(公告)号：US06807305B2

公开(公告)日：2004-10-19

申请号：US09832912

申请日：2001-04-10

Applicant: Ram Rajagopal ,  Lothar Wenzel ,  Dinesh Nair ,  Darren Schmidt

Inventor： Ram Rajagopal ,  Lothar Wenzel ,  Dinesh Nair ,  Darren Schmidt

IPC: G06K962

CPC classification number: G06F17/15 ,  G06K9/00496 ,  G06K9/52 ,  G06K9/522 ,  G06K9/6203

Abstract: A system and method for performing pattern matching to locate an instance of one or more of a plurality of template images in a target image. In a preprocessing phase a unified signal transform (UST) is determined from the template images. The UST converts each template image to a generalized frequency domain. The UST is applied at a generalized frequency to each template image to calculate corresponding generalized frequency component values (GFCVs) for each template image. At runtime, the target image is received, and the UST is applied at the generalized frequency to the target image to calculate a corresponding GFCV. The UST may be applied to pixel subsets of the template and target images. A best match is determined between the GFCV of the target image and the GFCVs of each template image. Finally, information indicating the best match template image from the set of template images is output.

Abstract translation: 一种用于执行图案匹配以定位目标图像中的多个模板图像中的一个或多个的实例的系统和方法。 在预处理阶段，从模板图像确定统一信号变换（UST）。 UST将每个模板图像转换为广义频域。 UST以广义频率应用于每个模板图像，以计算每个模板图像的相应的广义频率分量值（GFCV）。 在运行时，接收目标图像，并以广义频率将UST应用于目标图像，以计算相应的GFCV。 UST可以应用于模板和目标图像的像素子集。 在目标图像的GFCV和每个模板图像的GFCV之间确定最佳匹配。 最后，输出指示模板图像集合中最佳匹配模板图像的信息。

公开(公告)号：US06615158B2

公开(公告)日：2003-09-02

申请号：US09891566

申请日：2001-06-25

Applicant: Lothar Wenzel ,  Dinesh Nair ,  Ram Rajagopal

Inventor： Lothar Wenzel ,  Dinesh Nair ,  Ram Rajagopal

IPC: G06F300

CPC classification number: G06K9/28 ,  G06F17/18 ,  G06T7/0004 ,  G06T2200/04 ,  G06T2207/10028 ,  G06T2207/30164

Abstract: A system and method for analyzing a surface. The system includes a computer including a CPU and a memory medium operable to store programs executable by the CPU to perform the method. The method may include: 1) receiving data describing an n-dimensional surface defined in a bounded n-dimensional space, where the surface is embedded in an m-dimensional real space via embedding function x( ), and where m>n; 2) determining a diffeomorphism f of the n-dimensional space; 3) computing the inverse transform f−1 of the diffeomorphism f; 4) selecting points, e.g., a Low Discrepancy Sequence, in the n-dimensional space; 5) mapping the points onto the surface using x(f−1), thereby generating mapped points on the surface; 6) sampling the surface using at least a subset of the mapped points to generate samples of the surface; and 7) analyzing the samples of the surface to determine characteristics of the surface.

Abstract translation: 用于分析表面的系统和方法。 该系统包括一个计算机，它包括一个CPU和一个可操作的存储介质，用于存储由CPU执行的程序来执行该方法。 该方法可以包括：1）接收描述在有限的n维空间中定义的n维表面的数据，其中通过嵌入函数x（）将表面嵌入在m维实际空间中，并且其中m> n; 2）确定n维空间的不同形态f; 3）计算不同形式f的逆变换f-1; 4）在n维空间中选择点，例如低差异序列; 5）使用x（f-1）将点映射到表面上，从而在表面上生成映射点; 6）使用映射点的至少一个子集对表面进行采样，以生成表面样本; 和7）分析表面的样品以确定表面的特征。

公开(公告)号：US06229921B1

公开(公告)日：2001-05-08

申请号：US09227508

申请日：1999-01-06

Applicant: Lothar Wenzel ,  Dinesh Nair ,  Nicolas Vazquez ,  Samson DeKey

Inventor： Lothar Wenzel ,  Dinesh Nair ,  Nicolas Vazquez ,  Samson DeKey

IPC: G06K962

CPC classification number: G06K9/6203 ,  G06K2209/19 ,  G06T7/223 ,  G06T7/248 ,  G06T7/74 ,  G06T2207/10016 ,  G06T2207/30108

Abstract: A system and method for performing pattern matching to locate zero or more instances of a template image in a target image. The method first comprises sampling the template image using a Low Discrepancy sequence, also referred to as a quasi-random sequence, to determine a plurality of sample pixels in the template image which accurately characterize the template image. The Low Discrepancy sequence is designed to produce sample points which maximally avoid each other. After the template image is sampled or characterized, the method then performs pattern matching using the sample pixels and the target image to determine zero or more locations of the template image in the target image. The method may also perform a local stability analysis around at least a subset of the sample pixels to determine a lesser third number of sample pixels which have a desired degree of stability, and then perform pattern matching using the third plurality of sample pixels. In one embodiment, the local stability analysis determines a plurality of sets of sample pixels with differing stability neighborhood sizes, and the pattern matching performs a plurality of iterations of pattern matching using different sets of sample pixels, preferably performed in a coarse to fine manner, e.g., using sets of sample pixels with successively smaller stability neighborhood sizes and/or step sizes. The present invention also includes performing rotation invariant pattern matching by sampling the template image along one or more rotationally invariant paths, preferably circular perimeters, to produce one or more sets of sample pixels. These sample pixels from the circular paths are then used in the pattern matching. The rotationally invariant pattern matching may also use local stability analysis and coarse to fine searching techniques.

Abstract translation: 一种用于执行模式匹配以在目标图像中定位模板图像的零个或多个实例的系统和方法。 该方法首先包括使用低差异序列（也称为准随机序列）对模板图像进行采样，以确定模板图像中准确表征模板图像的多个样本像素。 低差异序列被设计为产生最大程度地避免彼此的采样点。 在模板图像被采样或表征之后，该方法然后使用样本像素和目标图像执行模式匹配，以确定目标图像中模板图像的零个或多个位置。 该方法还可以围绕样本像素的至少一个子集执行局部稳定性分析，以确定具有期望程度的稳定性的较小的第三数量的采样像素，然后使用第三多个采样像素执行模式匹配。 在一个实施例中，本地稳定性分析确定具有不同稳定性邻域大小的多组样本像素，并且模式匹配使用不同的采样像素集合执行多次迭代的模式匹配，优选地以粗略到精细的方式执行， 例如，使用具有连续更小的稳定性邻域大小和/或步长的样本像素集合。 本发明还包括通过沿着一个或多个旋转不变路径（优选圆周周长）采样模板图像来执行旋转不变模式匹配，以产生一组或多组采样像素。 来自圆形路径的这些采样像素然后用于模式匹配。 旋转不变模式匹配还可以使用局部稳定性分析和粗略到精细搜索技术。

公开(公告)号：US09117375B2

公开(公告)日：2015-08-25

申请号：US13169550

申请日：2011-06-27

Applicant: David Labine ,  Lothar Wenzel ,  Albert Chu

Inventor： David Labine ,  Lothar Wenzel ,  Albert Chu

IPC: G09B19/00 ,  G09B7/00 ,  G09B19/02 ,  G09B5/00 ,  G09B7/08 ,  G09B7/02

CPC classification number: G09B7/08 ,  G09B19/02

Abstract: A computerized assessment grading method comprises creating a syntax tree for a received equation-based response to at least one assessment question and a syntax tree for at least one solution to the at least one question, comparing the syntax trees, and grading the response based on the results of the comparison.

Abstract translation: 计算机化评估分级方法包括为至少一个评估问题和至少一个问题的至少一个解决方案的语法树创建所接收的基于方程式的响应的语法树，比较语法树，以及基于 比较结果。