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

US06614926B1 Methods and apparatuses for generating from an image a model of an object 有权
标题翻译：从图像生成对象的模型的方法和装置
公开(公告)号：US06614926B1
公开(公告)日：2003-09-02
申请号：US09605441
申请日：2000-06-28
申请人： Raymond Fix , Ivan Bachelder
发明人： Raymond Fix , Ivan Bachelder
IPC分类号： G06K946
CPC分类号： G06T7/0004
摘要： The invention provides methods and apparatuses for generating from an image of an object a model of the object, when the object contains similar features. First, the invention finds the similar features. The similar features are found by searching portions of the image for features that are substantially similar to a feature prototype. More particularly, individual features in the image are located and designated candidate features, and optionally a spatial pattern representing a majority of the candidate features is generated. Next, feature profiles are generated therefrom, and the feature prototype is constructed using at least a subset of feature profiles. Thereafter, the model is generated using the similar features and, optionally, the spatial pattern. An example is described wherein the model is of a ball grid array, the similar features are the solder balls on the ball grid array, the feature profiles are local images of balls of a ball grid array, and the feature prototype is an average of a sub-set of the local images of the balls.
摘要翻译：本发明提供了当对象包含相似特征时从对象的图像生成对象的模型的方法和装置。首先，本发明找到相似的特征。通过搜索与特征原型大致相似的特征的图像的部分来找到相似的特征。更具体地，图像中的各个特征位于并指定候选特征，并且可选地，生成表示候选特征的大部分的空间图案。接下来，从其生成特征轮廓，并且使用至少一个特征轮廓的子集来构造特征原型。此后，使用类似的特征和可选的空间模式来生成模型。描述了其中模型是球栅阵列的示例，类似的特征是球栅阵列上的焊球，特征轮廓是球栅阵列的球的局部图像，特征原型是球的局部图像的子集。

2. 发明申请

US20150363661A1 METHODS AND APPARATUS FOR ONE-DIMENSIONAL SIGNAL EXTRACTION 有权
标题翻译：用于一维信号提取的方法和装置
公开(公告)号：US20150363661A1
公开(公告)日：2015-12-17
申请号：US14837115
申请日：2015-08-27
申请人： William M. Silver , Ivan Bachelder
发明人： William M. Silver , Ivan Bachelder
IPC分类号： G06K9/46 , G06K9/62 , G06K7/14
CPC分类号： G06K9/18 , G06K7/00 , G06K7/10 , G06K7/10722 , G06K7/1413 , G06K7/1456 , G06K7/146 , G06K7/1478 , G06K9/00503 , G06K9/00973 , G06K9/46 , G06K9/50 , G06K9/62
摘要： Methods and apparatus are disclosed for extracting a one-dimensional digital signal from a two-dimensional digital image along a projection line. In some embodiments a repeating sequence of pixel weight templates, and a sequence of relative positions, are selected in response to the orientation of a projection line and used to compute a sequence of weighted sums. The sequence can be selected to achieve desirable properties, for example photometric accuracy, geometric accuracy, resolution, and/or noise reduction. In some embodiments registers and multiply-accumulators are arranged and controlled so as to compute the 1D signal.
摘要翻译：公开了用于从投影线从二维数字图像提取一维数字信号的方法和装置。在一些实施例中，响应于投影线的取向选择像素权重模板的重复序列和相对位置的序列，并用于计算加权和的序列。可以选择该顺序以获得期望的性质，例如光度精度，几何精度，分辨率和/或降噪。在一些实施例中，布置和控制寄存器和乘法累加器以便计算1D信号。

3. 发明授权

US07162073B1 Methods and apparatuses for detecting classifying and measuring spot defects in an image of an object 有权
标题翻译：用于检测物体的图像中的斑点缺陷的分类和测量的方法和装置
公开(公告)号：US07162073B1
公开(公告)日：2007-01-09
申请号：US10001177
申请日：2001-11-30
申请人： Yusuf Akgul , Ivan Bachelder , Adam Wagman , Jason Davis , Juha Koljonen , Prabhav Morje
发明人： Yusuf Akgul , Ivan Bachelder , Adam Wagman , Jason Davis , Juha Koljonen , Prabhav Morje
IPC分类号： G06K9/00 , G01N21/00
CPC分类号： G01N21/8851 , G06K9/38 , G06K2209/19 , G06T7/0004 , G06T7/174 , G06T7/194 , G06T2207/10056 , G06T2207/20081 , G06T2207/30108
摘要： A method is provided for detecting spot defects on an object when an allowable variation (called the “background”) in the appearance of the object can be modeled. Methods are also provided for measuring and classifying detected spot defects. An alignment model is used to align the image of the object, a background model is then used to estimate the (possibly different) background in each region, and each background is substantially removed from the image so as to form a foreground image on which blob analysis can be applied to detect spot defects, the blob analysis using a threshold image that accommodates different noise statistics for each region. The method facilitates robust spot defect inspection of fiber optic end faces, or of any object with different object regions. The method also allows use of blob analysis over a larger range of conditions, including conditions that make simple blob analysis infeasible.
摘要翻译：提供了一种用于在物体的外观中允许的变化（称为“背景”）来建模时，用于检测物体上的斑点缺陷的方法。还提供了用于测量和分类检测到的斑点缺陷的方法。使用对准模型对准对象的图像，然后使用背景模型来估计每个区域中的（可能不同的）背景，并且基本上从图像中删除每个背景，以便形成在其上的前景图像可以应用分析来检测斑点缺陷，使用适应每个区域的不同噪声统计的阈值图像进行斑点分析。该方法有助于光纤端面或具有不同物体区域的任何物体的鲁棒斑点缺陷检测。该方法还允许在更大范围的条件下使用斑点分析，包括使简单斑点分析不可行的条件。

4. 发明授权

US06993177B1 Gauging based on global alignment and sub-models 有权
标题翻译：基于全局校准和子模型的测量
公开(公告)号：US06993177B1
公开(公告)日：2006-01-31
申请号：US10000413
申请日：2001-11-02
申请人： Ivan Bachelder
发明人： Ivan Bachelder
IPC分类号： G06K9/00
CPC分类号： G06K9/6203
摘要： A method for accurately and efficiently determining the location of points or entities in a machine vision image. A set of sub-models are constructed from a global training model representing objects viewed by the machine vision system. The set of sub-models are used to fix the actual location of user selected points or entities. Configuration of the sub-models is automated to ensure that the sub-models contain sufficiently stable features within optimally sized regions without requiring substantial user expertise. Located entities are compared to evaluate compliance with pre-selected tolerances.
摘要翻译：一种用于准确有效地确定机器视觉图像中的点或实体的位置的方法。一组子模型由代表机器视觉系统观察的对象的全球训练模型构建。子模型集用于修正用户选择的点或实体的实际位置。子模型的配置是自动化的，以确保子模型在最佳尺寸的区域内包含足够稳定的特征，而不需要实质的用户专业知识。比较位置实体以评估符合预先设定的公差。

5. 发明授权

US06898333B1 Methods and apparatus for determining the orientation of an object in an image 失效
标题翻译：用于确定图像中物体的取向的方法和装置
公开(公告)号：US06898333B1
公开(公告)日：2005-05-24
申请号：US09629245
申请日：2000-07-31
申请人： Venkat Gopalakrishnan , Albert Montillo , Ivan Bachelder
发明人： Venkat Gopalakrishnan , Albert Montillo , Ivan Bachelder
IPC分类号： G06K9/36
CPC分类号： G06K9/522 , G06K9/3275
摘要： A method and an apparatus are disclosed for finding an orientation of an object from the image of the object through the generation of, and subsequent evaluation of, at least a portion of a frequency response of the image. The orientation of the object can be used in subsequent image processing.
摘要翻译：公开了一种方法和装置，用于通过对图像的频率响应的至少一部分的产生和随后的评估来从对象的图像中找到对象的取向。对象的方向可用于后续图像处理。

6. 发明授权

US06853751B1 Location of generally rectangular shaped objects in an image 失效
标题翻译：图像中大致长方形物体的位置
公开(公告)号：US06853751B1
公开(公告)日：2005-02-08
申请号：US09688205
申请日：2000-10-16
申请人： Robert Milligan, Jr. , Ivan Bachelder
发明人： Robert Milligan, Jr. , Ivan Bachelder
IPC分类号： G06K9/46 , G06K9/48
CPC分类号： G06K9/4609
摘要： A rectangle finder tool automatically locates rectangles in an image that correspond to substantially rectangular devices in the image. The rectangle finder tool can be used to automatically locate rectangles in an image or to generate abstract rectangular models of devices in the image. The tool determines the properties of and locates the rectangular device by searching for pairs of lines in an image at a specified orientation.
摘要翻译：矩形查找器工具自动定位与图像中的大致矩形设备相对应的图像中的矩形。矩形查找器工具可用于自动定位图像中的矩形或生成图像中的抽象矩形模型的设备。该工具通过在指定方向上搜索图像中的线对来确定矩形设备的属性并定位矩形设备。

7. 发明授权

US06639624B1 Machine vision methods for inspection of leaded components 有权
标题翻译：用于检查含铅元件的机器视觉方法
公开(公告)号：US06639624B1
公开(公告)日：2003-10-28
申请号：US09547590
申请日：2000-04-11
申请人： Ivan Bachelder , Karen Roberts , Aaron Wallack , William Silver , Edward Collins , Karen Sarachik
发明人： Ivan Bachelder , Karen Roberts , Aaron Wallack , William Silver , Edward Collins , Karen Sarachik
IPC分类号： H04N718
CPC分类号： G06T7/001 , G01R31/2813 , G06T7/74 , G06T2207/30148 , G06T2207/30152
摘要： A machine vision method for locating a leaded electronic device, such as integrated circuit chips, includes searching the image with a template depicting only a portion—e.g., one or two “side” edges—of each of one or more of the leads expected on the device. The template can include portions representing expected leads, as well as unexpected leads or unexpected lead positions. Positive and negative weightings are applied to such portions, as appropriate. A location of the device, or of one or more of its leads, is based on the results of the search.
摘要翻译：用于定位诸如集成电路芯片的引导电子设备的机器视觉方法包括用仅描绘期望的一个或多个引线中的每一个的一部分（例如，一个或两个“侧”边）的模板来搜索图像装置。该模板可以包括表示预期潜在客户的部分，以及意外的潜在客户或意外的潜在客户。适当地将正，负加权应用于这些部分。设备的位置或其一个或多个潜在客户的位置是基于搜索结果。

8. 发明授权

US09122952B2 Methods and apparatus for one-dimensional signal extraction 有权
标题翻译：一维信号提取的方法和装置
公开(公告)号：US09122952B2
公开(公告)日：2015-09-01
申请号：US13336275
申请日：2011-12-23
申请人： William M. Silver , Ivan Bachelder
发明人： William M. Silver , Ivan Bachelder
IPC分类号： G06K9/62 , G06K9/00 , G06K9/40 , G06K9/46 , G06K7/00 , G06K7/14
CPC分类号： G06K9/18 , G06K7/00 , G06K7/10 , G06K7/10722 , G06K7/1413 , G06K7/1456 , G06K7/146 , G06K7/1478 , G06K9/00503 , G06K9/00973 , G06K9/46 , G06K9/50 , G06K9/62
摘要： Methods and apparatus are disclosed for extracting a one-dimensional digital signal from a two-dimensional digital image along a projection line. In some embodiments a repeating sequence of pixel weight templates, and a sequence of relative positions, are selected in response to the orientation of a projection line and used to compute a sequence of weighted sums. The sequence can be selected to achieve desirable properties, for example photometric accuracy, geometric accuracy, resolution, and/or noise reduction. In some embodiments registers and multiply-accumulators are arranged and controlled so as to compute the 1D signal.
摘要翻译：公开了用于从投影线从二维数字图像提取一维数字信号的方法和装置。在一些实施例中，响应于投影线的取向选择像素权重模板的重复序列和相对位置的序列，并用于计算加权和的序列。可以选择该顺序以获得期望的性质，例如光度精度，几何精度，分辨率和/或降噪。在一些实施例中，布置和控制寄存器和乘法累加器以便计算1D信号。

9. 发明申请

US20130163876A1 Methods and Apparatus for One-Dimensional Signal Extraction 有权
标题翻译：一维信号提取方法与装置
公开(公告)号：US20130163876A1
公开(公告)日：2013-06-27
申请号：US13336275
申请日：2011-12-23
申请人： William M. Silver , Ivan Bachelder
发明人： William M. Silver , Ivan Bachelder
IPC分类号： G06K9/46
CPC分类号： G06K9/18 , G06K7/00 , G06K7/10 , G06K7/10722 , G06K7/1413 , G06K7/1456 , G06K7/146 , G06K7/1478 , G06K9/00503 , G06K9/00973 , G06K9/46 , G06K9/50 , G06K9/62
摘要： Methods and apparatus are disclosed for extracting a one-dimensional digital signal from a two-dimensional digital image along a projection line. In some embodiments a repeating sequence of pixel weight templates, and a sequence of relative positions, are selected in response to the orientation of a projection line and used to compute a sequence of weighted sums. The sequence can be selected to achieve desirable properties, for example photometric accuracy, geometric accuracy, resolution, and/or noise reduction. In some embodiments registers and multiply-accumulators are arranged and controlled so as to compute the 1D signal.
摘要翻译：公开了用于从投影线从二维数字图像提取一维数字信号的方法和装置。在一些实施例中，响应于投影线的取向选择像素权重模板的重复序列和相对位置的序列，并用于计算加权和的序列。可以选择该顺序以获得期望的性质，例如光度精度，几何精度，分辨率和/或降噪。在一些实施例中，布置和控制寄存器和乘法累加器以便计算1D信号。

10. 发明授权

US06941016B1 Method for finding contours in an image of an object 失效
标题翻译：在物体图像中查找轮廓的方法
公开(公告)号：US06941016B1
公开(公告)日：2005-09-06
申请号：US10035993
申请日：2001-12-31
申请人： Adam Wagman , Ivan Bachelder
发明人： Adam Wagman , Ivan Bachelder
IPC分类号： G06K9/48 , G06T5/00
CPC分类号： G06T7/0004 , G06K9/4638 , G06K9/48 , G06K2009/488 , G06T5/005 , G06T7/12 , G06T7/181 , G06T2207/10056 , G06T2207/20021 , G06T2207/30108
摘要： A method is provided for robustly and efficiently identifying contours in an image of an object. Features are extracted from an image, typically using a Sobel edge detector or a set of large oriented filters, and are locally chained to form contour segments of particular character, such as line segments. A spatial hash table is used to access the contour segments according to the location of their endpoints. Candidate sets for joining to grow contours are reduced by considering only segments having ends in adjacent spatial hash bins. Contour constraints are applied to appropriately choose among the candidates to form contours. The method facilitates robust and efficient scratch detection of fiber-optic end faces, or of any surface that may have smoothly curved scratches.
摘要翻译：提供了一种用于鲁棒且有效地识别对象的图像中的轮廓的方法。特征是从图像中提取的，通常使用Sobel边缘检测器或一组大的定向滤光片，并且被局部链接以形成特定字符的轮廓段，例如线段。空间哈希表用于根据其端点的位置访问轮廓段。通过仅考虑在相邻空间哈希仓中具有末端的段来减少用于加入轮廓的候选集。轮廓约束适用于候选人之间的适当选择以形成轮廓。该方法有助于光纤端面或任何可能具有平滑弯曲划痕的表面的鲁棒和有效的划痕检测。

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