专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06219452B1 Pattern matching system and method which performs local stability analysis for improved efficiency 有权
标题翻译：模式匹配系统和方法进行局部稳定性分析，提高效率
公开(公告)号：US06219452B1
公开(公告)日：2001-04-17
申请号：US09227506
申请日：1999-01-06
申请人： Dinesh Nair , Lothar Wenzel , Nicolas Vazquez , Samson DeKey
发明人： Dinesh Nair , Lothar Wenzel , Nicolas Vazquez , Samson DeKey
IPC分类号： G06K964
CPC分类号： G06K9/6203 , G06T7/223 , G06T7/248 , G06T7/74 , G06T2207/10016 , G06T2207/30108
摘要： 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.
摘要翻译：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。

2. 发明授权

US06370270B1 System and method for sampling and/or placing objects using low discrepancy sequences 有权
标题翻译：使用低差异序列采样和/或放置物体的系统和方法
公开(公告)号：US06370270B1
公开(公告)日：2002-04-09
申请号：US09385121
申请日：1999-08-27
申请人： Dinesh Nair , Lothar Wenzel , Nicolas Vazquez , Samson DeKey
发明人： Dinesh Nair , Lothar Wenzel , Nicolas Vazquez , Samson DeKey
IPC分类号： G06K962
CPC分类号： G06K9/6203 , G06K2209/19 , G06T7/223 , G06T7/248 , G06T7/74 , G06T2207/10016 , G06T2207/30108
摘要： 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.
摘要翻译：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。

3. 发明授权

US06222940B1 Pattern matching system and method which detects rotated and scaled template images 有权
标题翻译：模式匹配系统和方法，用于检测旋转和缩放的模板图像
公开(公告)号：US06222940B1
公开(公告)日：2001-04-24
申请号：US09227507
申请日：1999-01-06
申请人： Lothar Wenzel , Dinesh Nair , Nicolas Vazquez , Samson Dekey
发明人： Lothar Wenzel , Dinesh Nair , Nicolas Vazquez , Samson Dekey
IPC分类号： G06K964
CPC分类号： G06K9/6203 , G06T7/223 , G06T7/248 , G06T7/74 , G06T2207/10016 , G06T2207/30108
摘要： 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.
摘要翻译：一种用于执行模式匹配以在目标图像中定位零个或多个模板图像实例的系统和方法。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。

4. 发明授权

US06229921B1 Pattern matching system and method with improved template image sampling using low discrepancy sequences 有权
标题翻译：模式匹配系统和方法，使用低差异序列改进模板图像采样
公开(公告)号：US06229921B1
公开(公告)日：2001-05-08
申请号：US09227508
申请日：1999-01-06
申请人： Lothar Wenzel , Dinesh Nair , Nicolas Vazquez , Samson DeKey
发明人： Lothar Wenzel , Dinesh Nair , Nicolas Vazquez , Samson DeKey
IPC分类号： G06K962
CPC分类号： G06K9/6203 , G06K2209/19 , G06T7/223 , G06T7/248 , G06T7/74 , G06T2207/10016 , G06T2207/30108
摘要： 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.
摘要翻译：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。

5. 发明授权

US07397956B2 Pattern matching method selection 有权
标题翻译：模式匹配方法选择
公开(公告)号：US07397956B2
公开(公告)日：2008-07-08
申请号：US11763902
申请日：2007-06-15
申请人： Lothar Wenzel , Nicolas Vazquez , Kevin L. Schultz , Dinesh Nair
发明人： Lothar Wenzel , Nicolas Vazquez , Kevin L. Schultz , Dinesh Nair
IPC分类号： G06K9/62
CPC分类号： G06T7/0004 , G06K9/6857
摘要： A system and method for performing pattern matching to locate zero or more instances of a template image in a target image. An image is received by a computer from an image source, e.g., a camera. First pattern matching is performed on the image using a first pattern matching technique to determine a plurality of candidate areas. Second pattern matching is performed on each of the candidate areas using a second different pattern matching technique to generate final pattern match results. An output is generated indicating the final pattern match results. The second pattern matching may determine a second plurality of candidate areas which may be analyzed to determine the final pattern match results. The first pattern matching may use a plurality of pattern matching techniques, the results of which may be used to select a best technique from the plurality of techniques to use for the second pattern match.
摘要翻译：一种用于执行模式匹配以在目标图像中定位零个或多个模板图像实例的系统和方法。计算机从图像源（例如相机）接收图像。使用第一模式匹配技术对图像执行第一模式匹配以确定多个候选区域。使用第二不同的模式匹配技术对每个候选区域执行第二模式匹配以生成最终模式匹配结果。生成指示最终模式匹配结果的输出。第二模式匹配可以确定可以被分析以确定最终模式匹配结果的第二多个候选区域。第一模式匹配可以使用多个模式匹配技术，其结果可以用于从用于第二模式匹配的多种技术中选择最佳技术。

6. 发明授权

US07233699B2 Pattern matching using multiple techniques 有权
标题翻译：使用多种技术的模式匹配
公开(公告)号：US07233699B2
公开(公告)日：2007-06-19
申请号：US10100418
申请日：2002-03-18
申请人： Lothar Wenzel , Nicolas Vazquez , Kevin L. Schultz , Dinesh Nair
发明人： Lothar Wenzel , Nicolas Vazquez , Kevin L. Schultz , Dinesh Nair
IPC分类号： G06K9/62
CPC分类号： G06T7/0004 , G06K9/6857
摘要： A system and method for performing pattern matching to locate zero or more instances of a template image in a target image. An image is received by a computer from an image source, e.g., a camera. First pattern matching is performed on the image using a first pattern matching technique to determine a plurality of candidate areas. Second pattern matching is performed on each of the candidate areas using a second different pattern matching technique to generate final pattern match results. An output is generated indicating the final pattern match results. The second pattern matching may determine a second plurality of candidate areas which may be analyzed to determine the final pattern match results. The first pattern matching may use a plurality of pattern matching techniques, the results of which may be used to select a best technique from the plurality of techniques to use for the second pattern match.
摘要翻译：一种用于执行模式匹配以在目标图像中定位零个或多个模板图像实例的系统和方法。计算机从图像源（例如相机）接收图像。使用第一模式匹配技术对图像执行第一模式匹配以确定多个候选区域。使用第二不同的模式匹配技术对每个候选区域执行第二模式匹配以生成最终模式匹配结果。生成指示最终模式匹配结果的输出。第二模式匹配可以确定可以被分析以确定最终模式匹配结果的第二多个候选区域。第一模式匹配可以使用多个模式匹配技术，其结果可以用于从用于第二模式匹配的多种技术中选择最佳技术。

7. 发明申请

US20070237396A1 Pattern Matching Method Selection 有权
标题翻译：模式匹配方法选择
公开(公告)号：US20070237396A1
公开(公告)日：2007-10-11
申请号：US11763902
申请日：2007-06-15
申请人： Lothar Wenzel , Nicolas Vazquez , Kevin Schultz , Dinesh Nair
发明人： Lothar Wenzel , Nicolas Vazquez , Kevin Schultz , Dinesh Nair
IPC分类号： G06K9/62
CPC分类号： G06T7/0004 , G06K9/6857
摘要： A system and method for performing pattern matching to locate zero or more instances of a template image in a target image. An image is received by a computer from an image source, e.g., a camera. First pattern matching is performed on the image using a first pattern matching technique to determine a plurality of candidate areas. Second pattern matching is performed on each of the candidate areas using a second different pattern matching technique to generate final pattern match results. An output is generated indicating the final pattern match results. The second pattern matching may determine a second plurality of candidate areas which may be analyzed to determine the final pattern match results. The first pattern matching may use a plurality of pattern matching techniques, the results of which may be used to select a best technique from the plurality of techniques to use for the second pattern match.
摘要翻译：一种用于执行模式匹配以在目标图像中定位零个或多个模板图像实例的系统和方法。计算机从图像源（例如相机）接收图像。使用第一模式匹配技术对图像执行第一模式匹配以确定多个候选区域。使用第二不同的模式匹配技术对每个候选区域执行第二模式匹配以生成最终模式匹配结果。生成指示最终模式匹配结果的输出。第二模式匹配可以确定可以被分析以确定最终模式匹配结果的第二多个候选区域。第一模式匹配可以使用多个模式匹配技术，其结果可以用于从用于第二模式匹配的多种技术中选择最佳技术。

8. 发明授权

US07937665B1 System and method for automatically generating a graphical program to implement a prototype 有权
标题翻译：用于自动生成图形程序以实现原型的系统和方法
公开(公告)号：US07937665B1
公开(公告)日：2011-05-03
申请号：US09595003
申请日：2000-06-13
申请人： Nicolas Vazquez , Jeffrey L. Kodosky , Ram Kudukoli , Kevin L. Schultz , Dinesh Nair , Christophe Caltagirone
发明人： Nicolas Vazquez , Jeffrey L. Kodosky , Ram Kudukoli , Kevin L. Schultz , Dinesh Nair , Christophe Caltagirone
IPC分类号： G06F3/048
CPC分类号： G05B19/0426 , G05B2219/23008 , G05B2219/23258 , G05B2219/40099 , Y10S715/965 , Y10S715/967 , Y10S715/97
摘要： A system and method for automatically generating a graphical program from a prototyping environment application. By utilizing an application specialized for developing solutions to problems in a particular domain, i.e., a prototyping environment, a user may develop a solution to a problem, i.e., a prototype. The prototype may comprise a series of functions that form an algorithm or process. Once the user has developed the desired prototype, the user may request the prototyping environment to automatically, i.e., programmatically, generate a graphical program implementing the prototype, e.g., in order to run the program independently of the prototyping environment. In various embodiments, the prototyping environment may be operable to generate any of various types of graphical programs. Once the graphical program has been generated, the program may be modified as desired, e.g., in order to include features not available from the prototyping environment that generated the program.
摘要翻译：一种用于从原型设计环境应用程序自动生成图形程序的系统和方法。通过利用专门用于开发特定领域（即原型设计环境）中的问题的解决方案的应用，用户可以开发解决问题的解决方案，即原型。原型可以包括形成算法或过程的一系列功能。一旦用户开发了所需的原型，用户可以自动请求原型设计环境，即以编程方式生成实现原型的图形程序，例如，以独立于原型环境运行程序。在各种实施例中，原型设计环境可以用于生成各种类型的图形程序中的任何一种。一旦生成了图形程序，程序可以根据需要进行修改，例如，以便包括从生成该程序的原型环境中不可用的特征。

9. 发明授权

US06763515B1 System and method for automatically generating a graphical program to perform an image processing algorithm 有权
标题翻译：用于自动生成图形程序以执行图像处理算法的系统和方法
公开(公告)号：US06763515B1
公开(公告)日：2004-07-13
申请号：US09587682
申请日：2000-06-05
申请人： Nicolas Vazquez , Jeffrey L. Kodosky , Ram Kudukoli , Kevin L. Schultz , Dinesh Nair , Christophe Caltagirone
发明人： Nicolas Vazquez , Jeffrey L. Kodosky , Ram Kudukoli , Kevin L. Schultz , Dinesh Nair , Christophe Caltagirone
IPC分类号： G06F944
CPC分类号： G06F8/36 , G06F8/34 , Y10S715/967
摘要： System and method for automatically generating a graphical program to perform an image processing algorithm. A user may develop an image processing algorithm in an image prototyping environment. The image prototyping environment enables the user to easily apply various image processing functions to an image and immediately see the results, in order to develop the desired algorithm. As the user applies each image processing function to an image, the function may be recorded as a step in a script. Once the user has developed an algorithm, the user may request the image prototyping environment to automatically generate a program implementing the image processing algorithm. In various embodiments, the prototyping environment may be operable to generate different types of programs, including text-based and graphical programs. For example, a text-based program may include function calls corresponding to each step in the script recorded while developing the image processing algorithm, while a graphical program may include nodes corresponding to the steps of the script. The generated program may be operable to display a user interface comprising controls for interactively changing various parameters used by the image processing functions. An application programming interface (API) provided by a graphical programming environment that supports the dynamic creation/editing of a graphical program is described. The image prototyping environment may interface with a graphical programming environment through such an API in order to generate a graphical program that implements an algorithm specified by a script.
摘要翻译：用于自动生成图形程序以执行图像处理算法的系统和方法。用户可以在图像原型环境中开发图像处理算法。图像原型环境使用户能够轻松地将各种图像处理功能应用于图像，并立即看到结果，以便开发所需的算法。当用户将每个图像处理功能应用于图像时，该功能可以被记录为脚本中的步骤。一旦用户开发了算法，用户可以请求图像原型环境来自动生成实现图像处理算法的程序。在各种实施例中，原型设计环境可以用于生成不同类型的程序，包括基于文本和图形程序。例如，基于文本的程序可以包括对应于在开发图像处理算法时记录的脚本中的每个步骤的功能调用，而图形程序可以包括与脚本的步骤相对应的节点。生成的程序可以可操作以显示包括用于交互地改变由图像处理功能使用的各种参数的控制的用户界面。描述由支持动态创建/编辑图形程序的图形编程环境提供的应用编程接口（API）。图像原型环境可以通过这样的API与图形编程环境接口，以便生成实现由脚本指定的算法的图形程序。

10. 发明授权

US08640027B2 System and method for configuring a hardware device to execute a prototype 有权
标题翻译：用于配置硬件设备执行原型的系统和方法
公开(公告)号：US08640027B2
公开(公告)日：2014-01-28
申请号：US10200091
申请日：2002-07-19
申请人： Sundeep Chandhoke , Nicolas Vazquez , Kevin L. Schultz
发明人： Sundeep Chandhoke , Nicolas Vazquez , Kevin L. Schultz
IPC分类号： G06F3/00 , G06F9/00 , G06F17/00
CPC分类号： G05B19/0426 , G05B2219/23008 , G05B2219/23258 , G05B2219/40099
摘要： A system and method for configuring a hardware device to execute a prototype is presented. The hardware device may include a programmable hardware element and/or a processor and memory. The prototype may comprise a software entity operable to perform a plurality of executable operations, wherein the prototype is created by a user without requiring user programming. For example, a prototyping environment may provide a library of operations that are specific to a particular problem domain and may enable the user to select various operations from the library for inclusion in the prototype. The prototyping environment may include a graphical user interface that is streamlined for interactively experimenting with various parameters or properties associated with the selected operations and seeing the effects of adjusting the parameters.
摘要翻译：提出了一种用于配置硬件设备来执行原型的系统和方法。硬件设备可以包括可编程硬件元件和/或处理器和存储器。原型可以包括可操作以执行多个可执行操作的软件实体，其中原型由用户创建而不需要用户编程。例如，原型设计环境可以提供特定于特定问题域的操作库，并且可以使得用户能够从库中选择包含在原型中的各种操作。原型设计环境可以包括图形用户界面，其被简化用于交互地实验与所选择的操作相关联的各种参数或属性，并且看到调整参数的效果。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式