公开(公告)号：US20100303337A1

公开(公告)日：2010-12-02

申请号：US12474778

申请日：2009-05-29

申请人： Aaron Wallack ,  David Michael

发明人： Aaron Wallack ,  David Michael

IPC分类号： G06K9/00

CPC分类号： B25J9/1697 ,  G06T7/0004 ,  G06T2207/20104

摘要： A method and system for specifying an area of interest in a 3D imaging system including a plurality of cameras that include at least first and second cameras wherein each camera has a field of view arranged along a camera distinct trajectory, the method comprising the steps of presenting a part at a location within the fields of view of the plurality of cameras, indicating on the part an area of interest that is within the field of view of each of the plurality of cameras, for each of the plurality of cameras: (i) acquiring at least one image of the part including the area of interest, (ii) identifying a camera specific field of interest within the field of view of the camera associated with the area of interest in the at least one image and (iii) storing the field of interest for subsequent use.

摘要翻译： 一种用于指定包括至少包括第一和第二相机的多个相机的3D成像系统中的感兴趣区域的方法和系统，其中每个相机具有沿着相机不同轨迹布置的视场，所述方法包括以下步骤： 在多个照相机的视野内的位置处的部分，对于多个照相机中的每一个，部分地指示在多个照相机中的每一个的视场内的感兴趣区域：（i） 获取包括感兴趣区域的部分的至少一个图像，（ii）在与所述至少一个图像中的感兴趣区域相关联的摄像机的视野范围内识别感兴趣的相机专用领域，以及（iii）存储 感兴趣的领域用于后续使用。

公开(公告)号：US06993192B1

公开(公告)日：2006-01-31

申请号：US10705288

申请日：2003-11-10

申请人： William Silver ,  Aaron Wallack ,  Adam Wagman

发明人： William Silver ,  Aaron 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：US06856698B1

公开(公告)日：2005-02-15

申请号：US10273855

申请日：2002-10-18

申请人： William Silver ,  Aaron Wallack ,  Adam Wagman

发明人： William Silver ,  Aaron Wallack ,  Adam Wagman

IPC分类号： G06K9/48 ,  G06K9/62 ,  G06K9/64

CPC分类号： G06K9/6204

摘要： A method and apparatus are provided for rapidly refining a given approximate location of a pattern to produce a more accurate location. The invention employs a multi-dimensional space that includes translation, orientation, and scale. The invention can serve as a replacement for the fine resolution phase of any coarse-fine system for pattern location. Patterns and images are represented by a feature-based description that can be translated, rotated, and scaled to arbitrary precision much faster than digital image re-sampling, and without pixel grid quantization errors. Thus, accuracy is not limited by the ability of a grid to represent small changes in position, orientation, or size (or other degrees of freedom). The invention determines an accurate object pose from an approximate starting pose in a small, fixed number of increments that is independent of the number of dimensions of the space, and independent of the distance between the starting and final poses, provided that the starting pose is within the “capture range” of the true pose. Thus, accuracy need not be sacrificed to keep execution time acceptable for practical applications. Specifying locations in four or more dimensions will often result in better matches between the pattern and image than two-dimensional location systems, thereby improving accuracy. Accuracy is not degraded if some portion of the object is missing or occluded, or if unexpected extra features are present.

摘要翻译： 提供了一种方法和装置，用于快速地精化图案的给定的近似位置以产生更准确的位置。 本发明采用包括平移，取向和尺度的多维空间。 本发明可以作为用于图案定位的任何粗细系统的精细分辨率相位的替代。 模式和图像由基于特征的描述表示，其可以比数字图像重新采样更快地转换，旋转和缩放到任意精度，并且没有像素网格量化误差。 因此，精度不受网格表示位置，方向或大小（或其他自由度）的小变化的能力的限制。 本发明根据独立于空间的数量的小的固定数量的增量来确定来自近似起始姿态的准确的物体姿态，并且独立于起始和最终姿态之间的距离，只要起始姿势为 在“拍摄范围”内的真实姿势。 因此，不需要牺牲精度来保持实际应用可接受的执行时间。 在四维或更多维度上指定位置通常会导致图形和图像之间比二维位置系统更好的匹配，从而提高准确性。 如果对象的某些部分丢失或遮挡，或者如果出现意外的额外特征，则精度不会降低。

公开(公告)号：US06748104B1

公开(公告)日：2004-06-08

申请号：US09535633

申请日：2000-03-24

申请人： Ivan Bachelder ,  Aaron Wallack

发明人： Ivan Bachelder ,  Aaron Wallack

IPC分类号： G06K900

CPC分类号： G06T7/001 ,  G06T7/74 ,  G06T2207/30141 ,  G06T2207/30148

摘要： A method for rapid determination of the position and/or orientation of a semiconductor device, electronic component or other object includes performing multiple times an operation of matching a pattern against an image. The matching operation finds the location, if any, of a respective pattern in the image and determines the degree of match. The position and orientation of the object is determined from the results of one of the matching operations, for example, from the operation that revealed the highest degree of match.

摘要翻译： 一种用于快速确定半导体器件，电子部件或其他物体的位置和/或取向的方法包括执行多次将图案与图像匹配的操作。 匹配操作找到图像中相应图案的位置（如果有的话），并确定匹配度。 对象的位置和方向根据匹配操作之一的结果确定，例如从显示最高匹配度的操作中确定。

公开(公告)号：US07242801B1

公开(公告)日：2007-07-10

申请号：US10443580

申请日：2003-05-22

申请人： Aaron Wallack ,  Juha Koljonen ,  David Michael

发明人： Aaron Wallack ,  Juha Koljonen ,  David Michael

IPC分类号： G06K9/34

CPC分类号： G06T5/002 ,  G06T5/10 ,  G06T5/20 ,  G06T7/0004 ,  G06T2207/20056 ,  G06T2207/30148

摘要： Digital image processing methods are applied to an image of a semiconductor interconnection pad to preprocess the image prior to an inspection or registration. An image of a semiconductor pads exhibiting spatial patterns from structure, texture or features are filtered without affecting features in the image not associated with structure or texture. The filtered image is inspected in a probe mark inspection operation.

摘要翻译： 数字图像处理方法应用于半导体互连焊盘的图像，以便在检查或注册之前对图像进行预处理。 在结构，纹理或特征上呈现空间图案的半导体焊盘的图像被过滤而不影响图像中与结构或纹理无关的特征。 在探针标记检查操作中检查过滤图像。

公开(公告)号：US06987875B1

公开(公告)日：2006-01-17

申请号：US10032168

申请日：2001-12-21

申请人： Aaron Wallack

发明人： Aaron Wallack

IPC分类号： G06K9/00

CPC分类号： G06T7/0008 ,  G06T2207/30148

摘要： A method and apparatus for inspection of probe marks made on the interconnection lands of semiconductor devices using machine vision is disclosed. An image of an interconnection land is analyzed, and features of the image that may constitute indicia of probe marks are refined through the application of a series of unique heuristic processes. The output of the method is measurement data that can be used to characterize and verify the processes used to electrically probe semiconductor devices.

摘要翻译： 公开了一种使用机器视觉检查在半导体器件的互连平台上形成的探针标记的方法和装置。 分析互连区域的图像，并通过应用一系列独特的启发式过程来改进可构成探针标记的图像的特征。 该方法的输出是可用于表征和验证用于电探测半导体器件的工艺的测量数据。

公开(公告)号：US06850646B1

公开(公告)日：2005-02-01

申请号：US10705295

申请日：2003-11-10

申请人： William Silver ,  Aaron Wallack ,  Adam Wagman

发明人： William Silver ,  Aaron Wallack ,  Adam Wagman

IPC分类号： G06T7/00 ,  G06K9/48

CPC分类号： G06K9/6206 ,  G06T7/74

摘要： A method and apparatus are provided for identifying diffe rences 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：US06690842B1

公开(公告)日：2004-02-10

申请号：US10114357

申请日：2002-04-02

申请人： William Silver ,  Arman Garakani ,  Aaron Wallack

发明人： William Silver ,  Arman Garakani ,  Aaron Wallack

IPC分类号： G06L932

CPC分类号： G06T7/12 ,  G06T2207/10016

摘要： The invention provides a fast, computationally inexpensive, and highly accurate method and apparatus for edge detection in a digital image, even for edges that are not substantially parallel to the axes of the pixel grid, by exploiting computationally inexpensive estimates of gradient magnitude and direction. In particular, the method includes the steps of: estimating gradient magnitude and direction at a plurality of regularly-spaced pixel points in the image so as to provide a plurality of estimates of gradient magnitude and direction, each such estimate being associated with a respective gradient point of a regularly-spaced gradient grid; using gradient direction associated with each gradient point to select a respective set of neighboring gradient points; comparing gradient magnitude associated with each gradient point with each gradient magnitude of the respective set of neighboring gradient magnitudes so as to determine which of the gradient magnitudes is a local maximum in approximately the gradient direction; and using the local maximum of gradient magnitude and a set of neighboring gradient magnitudes to determine an interpolated edge position along a one-dimensional gradient magnitude profile. Another aspect of the invention for providing two-dimensional edge position interpolation further includes the step of determining a plane position line normal to the gradient direction of a gradient point associated with the local maximum of gradient magnitude, the plane position line also passing through the interpolated edge position, along which plane position line at least one two-dimensional interpolated position of the edge can be determined.

摘要翻译： 本发明通过利用计算上便宜的梯度和方向的估计，为数字图像中的边缘检测提供了一种快速的，计算上便宜的且高度准确的方法和装置，即使对于基本上不平行于像素网格的轴的边缘也是如此。 特别地，该方法包括以下步骤：估计图像中的多个规则间隔的像素点处的梯度幅度和方向，以便提供梯度幅度和方向的多个估计，每个这样的估计与相应梯度相关联 一个规则间隔的梯度网格点; 使用与每个梯度点相关联的梯度方向来选择相应的相邻梯度点集合; 将与每个梯度点相关联的梯度幅度与各个相邻梯度幅度集合的每个梯度幅度进行比较，以便确定大致梯度方向上的哪个梯度幅度是局部最大值; 并且使用梯度幅度的局部最大值和一组相邻梯度幅度来确定沿着一维梯度幅度轮廓的内插边缘位置。 用于提供二维边缘位置插值的本发明的另一方面还包括以下步骤：确定与梯度大小的局部最大值相关联的梯度点的梯度方向垂直的平面位置线，该平面位置线也经过内插 边缘位置，沿着该位置线可以确定边缘的至少一个二维插值位置。

公开(公告)号：US5825483A

公开(公告)日：1998-10-20

申请号：US574666

申请日：1995-12-19

申请人： David Michael ,  Aaron Wallack

发明人： David Michael ,  Aaron Wallack

IPC分类号： G01B11/00 ,  G01B11/02 ,  G01B11/245 ,  G01N21/88 ,  G03F7/20 ,  G03F9/00 ,  H01L21/66 ,  G01N21/00

CPC分类号： G03F7/706 ,  G01B11/002 ,  G01B11/245 ,  G01N21/8806 ,  G03F9/70

摘要： A multiple field of view calibration plate is provided both for coordinating multiple fields of view of a plurality of cameras so as to facilitate determining the distance between features on a semiconductor wafer, each feature being disposed within a different field of view, and for correcting image distortion within each field of view. The multiple field of view calibration plate is particularly suited for use in semiconductor manufacturing, and includes a substantially rigid dimensionally-stable substrate having a systematic array of features that are sized such that more than one of the features can fit within a field of view. The array is of a spatial extent such that more than one of the fields of view are substantially filled with the features. Also, the systematic assay of features is characterized by a distribution density suitable for correcting image distortion within a field of view. The systematic array can be a regular array, each feature being separated from each nearest neighboring feature by an equal distance. Alternatively, the separation between neighboring features is a function of position on the substrate, so that given the relative location of two neighboring features, their position on the substrate can be deduced In addition, the substrate includes more than one landmark, each landmark being located at one of a plurality of possible camera positions, where the possible camera positions are of known relative position, so as to facilitate determining the distance between features each disposed within a different field of view.

摘要翻译： 提供了多视野校准板用于协调多个摄像机的多个视野，以便于确定半导体晶片上的特征之间的距离，每个特征被设置在不同的视野内，并且用于校正图像 每个视野内的失真。 多视场校准板特别适用于半导体制造，并且包括基本上刚性的尺寸稳定的衬底，其具有系统的特征阵列，其尺寸使得多于一个特征可以适应于视野范围。 该阵列具有空间范围，使得多个视场中的一个以基本上被特征填充。 此外，特征的系统测定的特征在于适于校正视场内的图像失真的分布密度。 系统阵列可以是规则阵列，每个特征与每个最近的相邻特征分开相等的距离。 或者，相邻特征之间的间隔是衬底上的位置的函数，因此给定两个相邻特征的相对位置，可以推断它们在衬底上的位置。此外，衬底包括多于一个的标记，每个标记位于 在多个可能的相机位置中的一个位置处，其中可能的相机位置是已知的相对位置，以便于确定每个设置在不同视场内的特征之间的距离。

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。