公开(公告)号：US06975764B1

公开(公告)日：2005-12-13

申请号：US10657522

申请日：2003-09-08

申请人： William Silver ,  Aaron Wallack ,  Adam Wagman

发明人： William Silver ,  Aaron Wallack ,  Adam Wagman

IPC分类号： G06T7/00 ,  G06K9/62 ,  G06K9/46 ,  G06K9/48

CPC分类号： G06K9/32 ,  G06K9/6203 ,  G06T7/75

摘要： A method and apparatus are provided for identifying differences between a stored pattern and a matching image subset, where variations in pattern position, orientation, and size do not give rise to false differences. The invention is also a system for analyzing an object image with respect to a model pattern so as to detect flaws in the object image. The system includes extracting pattern features from the model pattern; generating a vector-valued function using the pattern features to provide a pattern field; extracting image features from the object image; evaluating each image feature, using the pattern field and an n-dimensional transformation that associates image features with pattern features, so as to determine at least one associated feature characteristic; and using at least one feature characteristic to identify at least one flaw in the object image. The invention can find at least two distinct kinds of flaws: missing features, and extra features. The invention provides pattern inspection that is faster and more accurate than any known prior art method by using a stored pattern that represents an ideal example of the object to be found and inspected, and that can be translated, rotated, and scaled to arbitrary precision much faster than digital image re-sampling, and without pixel grid quantization errors. Furthermore, since the invention does not use digital image re-sampling, there are no pixel quantization errors to cause false differences between the pattern and image that can limit inspection performance.

摘要翻译： 提供了一种用于识别存储的图案和匹配图像子集之间的差异的方法和装置，其中图案位置，取向和尺寸的变化不会引起错误的差异。 本发明还是一种用于分析相对于模型图案的对象图像以便检测对象图像中的缺陷的系统。 该系统包括从模型模式中提取模式特征; 使用所述模式特征生成向量值函数以提供模式字段; 从对象图像提取图像特征; 使用所述图案字段和将图像特征与图案特征相关联的n维变换来评估每个图像特征，以便确定至少一个相关联的特征特征; 以及使用至少一个特征特征来识别所述对象图像中的至少一个缺陷。 本发明可以找到至少两种不同种类的缺陷：缺失特征和额外特征。 本发明提供了通过使用表示待发现和检查的对象的理想示例的存储模式并且可以被转换，旋转和按任意精度缩放的模式检查，其比任何已知的现有技术方法更快和更准确 比数字图像重采样更快，并且没有像素网格量化误差。 此外，由于本发明不使用数字图像再采样，因此不存在可能限制检查性能的图案和图像之间的误差的像素量化误差。

公开(公告)号：US08705851B2

公开(公告)日：2014-04-22

申请号：US13733685

申请日：2013-01-03

申请人： Simon Barker ,  Adam Wagman ,  Aaron Wallack ,  David J Michael

发明人： Simon Barker ,  Adam Wagman ,  Aaron Wallack ,  David J Michael

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/3275 ,  G06K9/6255 ,  G06K9/6857 ,  G06T7/74 ,  G06T2207/20081 ,  G06T2207/30208

摘要： A method for training a pattern recognition algorithm including the steps of identifying the known location of the pattern that includes repeating elements within a fine resolution image, using the fine resolution image to train a model associated with the fine image, using the model to examine the fine image resolution image to generate a score space, examining the score space to identify a repeating pattern frequency, using a coarse image that is coarser than the finest image resolution image to train a model associated with the coarse image, using the model associated with the coarse image to examine the coarse image thereby generating a location error, comparing the location error to the repeating pattern frequency and determining if the coarse image resolution is suitable for locating the pattern within a fraction of one pitch of the repeating elements.

摘要翻译： 一种用于训练模式识别算法的方法，包括以下步骤：使用所述模型来识别包含精细分辨率图像内的重复元素的图案的已知位置，使用所述精细分辨率图像来训练与所述精细图像相关联的模型， 精细图像分辨率图像以生成分数空间，使用与最粗图像分辨率图像相比较粗糙的图像来检查分数空间以识别重复图案频率，以使用与该图像相关联的模型来训练与粗图像相关联的模型 粗图像以检查粗图像，从而产生位置误差，将位置误差与重复图案频率进行比较，并确定粗图像分辨率是否适于将图案定位在重复元件的一个间距的几分之一内。

公开(公告)号：US20130182948A1

公开(公告)日：2013-07-18

申请号：US13733685

申请日：2013-01-03

申请人： Simon A. Barker ,  Adam Wagman ,  Aaron Wallack ,  David J. Michael

发明人： Simon A. Barker ,  Adam Wagman ,  Aaron Wallack ,  David J. Michael

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/3275 ,  G06K9/6255 ,  G06K9/6857 ,  G06T7/74 ,  G06T2207/20081 ,  G06T2207/30208

摘要： A method for training a pattern recognition algorithm including the steps of identifying the known location of the pattern that includes repeating elements within a fine resolution image, using the fine resolution image to train a model associated with the fine image, using the model to examine the fine image resolution image to generate a score space, examining the score space to identify a repeating pattern frequency, using a coarse image that is coarser than the finest image resolution image to train a model associated with the coarse image, using the model associated with the coarse image to examine the coarse image thereby generating a location error, comparing the location error to the repeating pattern frequency and determining if the coarse image resolution is suitable for locating the pattern within a fraction of one pitch of the repeating elements.

摘要翻译： 一种用于训练模式识别算法的方法，包括以下步骤：使用所述模型来识别包含精细分辨率图像内的重复元素的图案的已知位置，使用所述精细分辨率图像来训练与所述精细图像相关联的模型， 精细图像分辨率图像以生成分数空间，使用与最粗图像分辨率图像相比较粗糙的图像来检查分数空间以识别重复图案频率，以使用与该图像相关联的模型来训练与粗图像相关联的模型 粗图像以检查粗图像，从而产生位置误差，将位置误差与重复图案频率进行比较，并确定粗图像分辨率是否适于将图案定位在重复元件的一个间距的几分之一内。

公开(公告)号：US08457390B1

公开(公告)日：2013-06-04

申请号：US12249318

申请日：2008-10-10

申请人： Simon Barker ,  Adam Wagman ,  Aaron Wallack ,  David J. Michael

发明人： Simon Barker ,  Adam Wagman ,  Aaron Wallack ,  David J. Michael

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/3275 ,  G06K9/6255 ,  G06K9/6857 ,  G06T7/74 ,  G06T2207/20081 ,  G06T2207/30208

摘要： A method for training a pattern recognition algorithm for a machine vision system that uses models of a pattern to be located, the method comprising the steps of training each of a plurality of models using a different training image wherein each of the training images is a version of a single image of the pattern at a unique coarse image resolution, using the models to identify at least one robust image resolution where the image resolution is suitable for locating the pattern within an accuracy limit of the actual location of the pattern in the image and storing the at least one robust image resolution for use in subsequent pattern recognition processes.

摘要翻译： 一种训练用于使用要定位的模式的模型的机器视觉系统的模式识别算法的方法，所述方法包括以下步骤：使用不同的训练图像训练多个模型中的每一个，其中每个训练图像是版本 使用这些模型来识别至少一个鲁棒的图像分辨率，其中图像分辨率适合于将图案定位在图像的图案的实际位置的精度极限内，以及 存储用于后续模式识别过程的至少一个鲁棒图像分辨率。

公开(公告)号：US07251366B1

公开(公告)日：2007-07-31

申请号：US10705294

申请日：2003-11-10

申请人： William Silver ,  Araon Wallack ,  Adam Wagman

发明人： William Silver ,  Araon Wallack ,  Adam Wagman

IPC分类号： G06K9/62

CPC分类号： G06K9/32 ,  G06K9/6203 ,  G06T7/75

摘要： A method and apparatus are provided for identifying differences between a stored pattern and a matching image subset, where variations in pattern position, orientation, and size do not give rise to false differences. The invention is also a system for analyzing an object image with respect to a model pattern so as to detect flaws in the object image. The system includes extracting pattern features from the model pattern; generating a vector-valued function using the pattern features to provide a pattern field; extracting image features from the object image; evaluating each image feature, using the pattern field and an n-dimensional transformation that associates image features with pattern features, so as to determine at least one associated feature characteristic; and using at least one feature characteristic to identify at least one flaw in the object image. The invention can find at least two distinct kinds of flaws: missing features, and extra features. The invention provides pattern inspection that is faster and more accurate than any known prior art method by using a stored pattern that represents an ideal example of the object to be found and inspected, and that can be translated, rotated, and scaled to arbitrary precision much faster than digital image re-sampling, and without pixel grid quantization errors. Furthermore, since the invention does not use digital image re-sampling, there are no pixel quantization errors to cause false differences between the pattern and image that can limit inspection performance.

公开(公告)号：US06836567B1

公开(公告)日：2004-12-28

申请号：US10705495

申请日：2003-11-10

申请人： William Silver ,  Aaron Walleck ,  Adam Wagman

发明人： William Silver ,  Aaron Walleck ,  Adam Wagman

IPC分类号： G06K962

CPC分类号： G06K9/32 ,  G06K9/6203 ,  G06T7/75

摘要： A method and apparatus are provided for identifying differences between a stored pattern and a matching image subset, where variations in pattern position, orientation, and size do not give rise to false differences. The invention is also a system for analyzing an object image with respect to a model pattern so as to detect flaws in the object image. The system includes extracting pattern features from the model pattern; generating a vector-valued function using the pattern features to provide a pattern field; extracting image features from the object image; evaluating each image feature, using the pattern field and an n-dimensional transformation that associates image features with pattern features, so as to determine at least one associated feature characteristic; and using at least one feature characteristic to identify at least one flaw in the object image. The invention can find at least two distinct kinds of flaws; missing features, and extra features. The invention provides pattern inspection that is faster and more accurate than any known prior art method by using a stored pattern that represents an ideal example of the object to be found and inspected, and that can be translated, rotated, and scaled to arbitrary precision much faster than digital image re-sampling, and without pixel grid quantization errors. Furthermore, since the invention does not use digital image re-sampling, there are no pixel quantization errors to cause false differences between the pattern and image that can limit inspection performance.

摘要翻译： 提供了一种用于识别存储的图案和匹配图像子集之间的差异的方法和装置，其中图案位置，取向和尺寸的变化不会引起错误的差异。 本发明还是一种用于分析相对于模型图案的对象图像以便检测对象图像中的缺陷的系统。 该系统包括从模型模式中提取模式特征; 使用所述模式特征生成向量值函数以提供模式字段; 从对象图像提取图像特征; 使用所述图案字段和将图像特征与图案特征相关联的n维变换来评估每个图像特征，以便确定至少一个相关联的特征特征; 以及使用至少一个特征特征来识别所述对象图像中的至少一个缺陷。 本发明可以发现至少两种不同种类的缺陷; 缺少功能和额外功能。 本发明通过使用表示待发现和检查的对象的理想示例的存储模式，并且可以被转换，旋转和缩放到任意精度而提供比任何已知的现有技术方法更快更准确的模式检查 比数字图像重采样更快，并且没有像素网格量化误差。 此外，由于本发明不使用数字图像重新采样，因此不存在像素量化误差，导致图案和图像之间可能限制检查性能的误差。

公开(公告)号：US06658145B1

公开(公告)日：2003-12-02

申请号：US09746147

申请日：2000-12-22

申请人： William Silver ,  Aaron S. Wallack ,  Adam Wagman

发明人： William Silver ,  Aaron S. Wallack ,  Adam Wagman

IPC分类号： G06K900

CPC分类号： G06K9/6206 ,  G06T7/75

摘要： A method and apparatus are provided for identifying differences between a stored pattern and a matching image subset, where variations in pattern position, orientation, and size do not give rise to false differences. The invention is also a system for analyzing an object image with respect to a model pattern so as to detect flaws in the object image. The system includes extracting pattern features from the model pattern; generating a vector-valued function using the pattern features to provide a pattern field; extracting image features from the object image; evaluating each image feature, using the pattern field and an n-dimensional transformation that associates image features with pattern features, so as to determine at least one associated feature characteristic; and using at least one feature characteristic to identify at least one flaw in the object image. The invention can find at least two distinct kinds of flaws: missing features, and extra features. The invention provides pattern inspection that is faster and more accurate than any known prior art method by using a stored pattern that represents an ideal example of the object to be found and inspected, and that can be translated, rotated, and scaled to arbitrary precision much faster than digital image re-sampling, and without pixel grid quantization errors. Furthermore, since the invention does not use digital image re-sampling, there are no pixel quantization errors to cause false differences between the pattern and image that can limit inspection performance.

摘要翻译： 提供了一种用于识别存储的图案和匹配图像子集之间的差异的方法和装置，其中图案位置，取向和尺寸的变化不会引起错误的差异。 本发明还是一种用于分析相对于模型图案的对象图像以便检测对象图像中的缺陷的系统。 该系统包括从模型模式中提取模式特征; 使用所述模式特征生成向量值函数以提供模式字段; 从对象图像提取图像特征; 使用所述图案字段和将图像特征与图案特征相关联的n维变换来评估每个图像特征，以便确定至少一个相关联的特征特征; 以及使用至少一个特征特征来识别所述对象图像中的至少一个缺陷。 本发明可以发现至少两种不同种类的缺陷：缺失特征和额外特征。 本发明通过使用表示待发现和检查的对象的理想示例的存储模式，并且可以被转换，旋转和缩放到任意精度而提供比任何已知的现有技术方法更快更准确的模式检查 比数字图像重采样更快，并且没有像素网格量化误差。 此外，由于本发明不使用数字图像重新采样，因此不存在像素量化误差，导致图案和图像之间可能限制检查性能的误差。

公开(公告)号：US09412158B2

公开(公告)日：2016-08-09

申请号：US12194055

申请日：2008-08-19

申请人： Jason Adam Davis ,  Adam Wagman

发明人： Jason Adam Davis ,  Adam Wagman

IPC分类号： G06T7/00 ,  G06F9/44 ,  G06T1/20 ,  G06F9/50 ,  G05B19/42 ,  G05B19/042

CPC分类号： G06T7/0004 ,  G05B19/0421 ,  G05B2219/37208 ,  G06F8/314 ,  G06F9/5066 ,  G06F2209/5017 ,  G06F2209/504 ,  G06T1/20 ,  Y02P90/265

摘要： A machine vision system includes a computer with one or more processors and software that has a plurality of tool routines each performing a different image analysis function. A machine vision application program is created by selecting certain ones of the plurality of tool routines to analyze the image. A maximum number of processors on the computer is designated as available for executing a machine vision application, wherein the maximum number may be less than the total number of processors on the computer. When the machine vision application program operates execution of each tool routine is limited to using simultaneously no more than the maximum number of processors.

摘要翻译： 机器视觉系统包括具有一个或多个处理器的计算机和具有多个工具程序的软件，每个工具程序执行不同的图像分析功能。 通过选择多个工具例程中的某些来分析图像来创建机器视觉应用程序。 计算机上的最大处理器数量被指定为可用于执行机器视觉应用，其中最大数量可以小于计算机上的处理器总数。 当机器视觉应用程序操作每个工具程序的执行被限制为同时使用不超过最大数量的处理器。

公开(公告)号：US20130142421A1

公开(公告)日：2013-06-06

申请号：US13656167

申请日：2012-10-19

申请人： William M. Silver ,  E. John McGarry ,  Sanjay Nichani ,  Adam Wagman

发明人： William M. Silver ,  E. John McGarry ,  Sanjay Nichani ,  Adam Wagman

IPC分类号： G06K9/62

CPC分类号： G06K9/6201 ,  G06K9/481 ,  G06K9/6204

摘要： A method and system for probe-based pattern matching including an apparatus for synthetic training of a model of a pattern. The apparatus comprises a sensor for obtaining an image of the pattern and a processor for receiving the image of the pattern from the sensor and running a program. In the steps performed by the program a boundary of the pattern in the image is identified. A plurality of positive probes are placed at selected points along the boundary of the pattern and at least one straight segment of the boundary of the pattern is identified. The at least one straight segment of the boundary is extended to provide an imaginary straight segment and a plurality of negative probes are placed at selected points along the imaginary straight segment, where each negative probe has a negative weight.

摘要翻译： 一种用于基于探针的模式匹配的方法和系统，包括用于模式模型的合成训练的装置。 该装置包括用于获得图案的图像的传感器和用于从传感器接收图案的图像并运行程序的处理器。 在由程序执行的步骤中，识别图像中的图案的边界。 沿着图案的边界的选定点放置多个正探针，并且识别图案的边界的至少一个直线段。 边界的至少一个直线段被延伸以提供假想的直线段，并且多个负探针被放置在沿着假想直线段的选定点处，其中每个负探头具有负重。

公开(公告)号：US08363972B1

公开(公告)日：2013-01-29

申请号：US11027963

申请日：2004-12-31

申请人： William M. Silver ,  E. John McGarry ,  Matthew L. Hill ,  Nigel J. Foster ,  Sanjay Nichani ,  Willard P. Foster ,  Adam Wagman

发明人： William M. Silver ,  E. John McGarry ,  Matthew L. Hill ,  Nigel J. Foster ,  Sanjay Nichani ,  Willard P. Foster ,  Adam Wagman

IPC分类号： G06K9/62

CPC分类号： G06K9/6201 ,  G06K9/481 ,  G06K9/6204

摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.