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

US09715723B2 Optimization of unknown defect rejection for automatic defect classification 有权
公开(公告)号：US09715723B2
公开(公告)日：2017-07-25
申请号：US13451500
申请日：2012-04-19
申请人： Vladimir Shlain , Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
发明人： Vladimir Shlain , Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
IPC分类号： G06T7/00 , G06K9/03 , G06K9/62
CPC分类号： G06T7/0004 , G06K9/033 , G06K9/6269 , G06K9/6284 , G06T2207/10061 , G06T2207/20076 , G06T2207/20081 , G06T2207/30148
摘要： A method for defect classification includes storing, in a computer system, a definition of a region in a feature space. The definition is associated with a class of defects and comprises a kernel function comprising a parameter. The parameter determines a shape of the region. A confidence threshold for automatic classification of at least one defect associated with the class is received. A value of the parameter associated with the confidence threshold is selected. Inspection data for a plurality of defects detected in one or more samples under inspection is received. The plurality of defects for the class are automatically classified using the kernel function and the selected value of the parameter.

2. 发明申请

US20130279794A1 INTEGRATION OF AUTOMATIC AND MANUAL DEFECT CLASSIFICATION 审中-公开
标题翻译：自动和手动缺陷分类的整合
公开(公告)号：US20130279794A1
公开(公告)日：2013-10-24
申请号：US13451496
申请日：2012-04-19
申请人： Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
发明人： Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
IPC分类号： G06K9/00
CPC分类号： G06T7/001 , G06K9/033 , G06K9/6269 , G06K9/6284 , G06T2207/10061 , G06T2207/30148
摘要： A method for defect classification includes storing definitions of defect classes in terms of a classification rules in a multi-dimensional feature space. Inspection data associated with defects detected in one or more samples under inspection is received. A plurality of first classification results is generated by applying an automatic classifier to the inspection data based on the definitions, the plurality of first classification results comprising a class label and a corresponding confidence level for a defect. Upon determining that a confidence level for a defect is below a predetermined confidence threshold, a plurality of second classification results are generated by applying at least one inspection modality to the defect. A report is generated comprising a distribution of the defects among the defect classes by combining the plurality of first classification results and the plurality of second classification results.
摘要翻译：一种用于缺陷分类的方法包括根据多维特征空间中的分类规则存储缺陷类的定义。接收与在检查中的一个或多个样品中检测到的缺陷有关的检查数据。通过基于定义应用自动分类器来生成多个第一分类结果，多个第一分类结果包括类别标签和相应的缺陷置信度。在确定缺陷的置信水平低于预定置信度阈值时，通过对缺陷应用至少一种检查模式来生成多个第二分类结果。通过组合多个第一分类结果和多个第二分类结果，生成包括缺陷类别中的缺陷的分布的报告。

3. 发明申请

US20130279796A1 CLASSIFIER READINESS AND MAINTENANCE IN AUTOMATIC DEFECT CLASSIFICATION 有权
标题翻译：分类器在自动缺陷分类中的阅读和维护
公开(公告)号：US20130279796A1
公开(公告)日：2013-10-24
申请号：US13452771
申请日：2012-04-20
申请人： Idan Kaizerman , Vladimir Shlain , Efrat Rozenman
发明人： Idan Kaizerman , Vladimir Shlain , Efrat Rozenman
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/033 , G06K9/6256 , G06K9/6267 , G06T7/0004 , G06T7/001 , G06T2207/30148
摘要： A method for classification includes receiving inspection data associated with a plurality of defects found in one or more samples and receiving one or more benchmark classification comprising a class for each of the plurality of defects. a readiness criterion for one or more of the classes is evaluated based on the one or more benchmark classification results, wherein the readiness criterion comprises for each class, a suitability of the inspection data for training an automatic defect classifier for the class. A portion of the inspection data is selected corresponding to one or more defects associated with one or more classes that satisfy the readiness criterion. One or more automatic classifiers are trained for the one or more classes that satisfy the readiness criterion using the selected portion of the inspection data.
摘要翻译：一种用于分类的方法包括接收与一个或多个样本中发现的多个缺陷相关联的检查数据，并且接收一个或多个基准分类，其包括针对所述多个缺陷中的每一个的类别。基于一个或多个基准分类结果来评估一个或多个类的准备标准，其中准备准则包括对于每个类别，用于训练用于该类的自动缺陷分类器的检查数据的适合性。对应于与满足准备标准的一个或多个类别相关联的一个或多个缺陷来选择检查数据的一部分。使用检查数据的所选部分，针对满足准备标准的一个或多个类训练一个或多个自动分类器。

4. 发明申请

US20130279795A1 OPTIMIZATION OF UNKNOWN DEFECT REJECTION FOR AUTOMATIC DEFECT CLASSIFICATION 有权
标题翻译：自动缺陷分类的未知缺陷抑制优化
公开(公告)号：US20130279795A1
公开(公告)日：2013-10-24
申请号：US13451500
申请日：2012-04-19
申请人： Vladimir Shlain , Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
发明人： Vladimir Shlain , Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
IPC分类号： G06K9/62
CPC分类号： G06T7/0004 , G06K9/033 , G06K9/6269 , G06K9/6284 , G06T2207/10061 , G06T2207/20076 , G06T2207/20081 , G06T2207/30148
摘要： A method for defect classification includes storing, in a computer system, a definition of a region in a feature space. The definition is associated with a class of defects and comprises a kernel function comprising a parameter. The parameter determines a shape of the region. A confidence threshold for automatic classification of at least one defect associated with the class is received. A value of the parameter associated with the confidence threshold is selected. Inspection data for a plurality of defects detected in one or more samples under inspection is received. The plurality of defects for the class are automatically classified using the kernel function and the selected value of the parameter.
摘要翻译：一种用于缺陷分类的方法包括在计算机系统中存储特征空间中的区域的定义。该定义与一类缺陷相关联，并且包括包含参数的核心函数。该参数确定区域的形状。接收到与该类相关联的至少一个缺陷的自动分类的置信阈值。选择与置信阈值相关联的参数的值。接收在检查中的一个或多个样本中检测到的多个缺陷的检查数据。该类的多个缺陷使用内核函数和参数的选定值进行自动分类。

5. 发明授权

US10043264B2 Integration of automatic and manual defect classification 有权
公开(公告)号：US10043264B2
公开(公告)日：2018-08-07
申请号：US13451496
申请日：2012-04-19
申请人： Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
发明人： Gadi Greenberg , Idan Kaizerman , Efrat Rozenman
IPC分类号： G06T7/00 , G06K9/03 , G06K9/62
CPC分类号： G06T7/001 , G06K9/033 , G06K9/6269 , G06K9/6284 , G06T2207/10061 , G06T2207/30148
摘要： A method for defect classification includes storing definitions of defect classes in terms of a classification rules in a multi-dimensional feature space. Inspection data associated with defects detected in one or more samples under inspection is received. A plurality of first classification results is generated by applying an automatic classifier to the inspection data based on the definitions, the plurality of first classification results comprising a class label and a corresponding confidence level for a defect. Upon determining that a confidence level for a defect is below a predetermined confidence threshold, a plurality of second classification results are generated by applying at least one inspection modality to the defect. A report is generated comprising a distribution of the defects among the defect classes by combining the plurality of first classification results and the plurality of second classification results.

6. 发明申请

US20130279790A1 DEFECT CLASSIFICATION USING CAD-BASED CONTEXT ATTRIBUTES 有权
标题翻译：使用基于CAD的语境属性进行缺陷分类
公开(公告)号：US20130279790A1
公开(公告)日：2013-10-24
申请号：US13451486
申请日：2012-04-19
申请人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
发明人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
IPC分类号： G06K9/00
CPC分类号： G06T7/001 , G06T2207/10061 , G06T2207/30148
摘要： A method for classification includes receiving an image of an area of a semiconductor wafer on which a pattern has been formed, the area containing an image location of interest, and receiving computer-aided design (CAD) data relating to the pattern comprising a CAD location of interest corresponding to the image location of interest. At least one value for one or more attributes of the image location of interest is computed based on a context of the CAD location of interest with respect to the CAD data.
摘要翻译：一种用于分类的方法包括接收其上已经形成图案的半导体晶片的区域的图像，包含感兴趣的图像位置的区域，以及接收与包括CAD位置的图案相关的计算机辅助设计（CAD）数据对应于感兴趣的图像位置的兴趣。基于关于CAD数据的感兴趣的CAD位置的上下文来计算感兴趣的图像位置的一个或多个属性的至少一个值。

7. 发明授权

US09607233B2 Classifier readiness and maintenance in automatic defect classification 有权
公开(公告)号：US09607233B2
公开(公告)日：2017-03-28
申请号：US13452771
申请日：2012-04-20
申请人： Idan Kaizerman , Vladimir Shlain , Efrat Rozenman
发明人： Idan Kaizerman , Vladimir Shlain , Efrat Rozenman
IPC分类号： G06K9/00 , G06K9/03 , G06K9/62 , G06T7/00
CPC分类号： G06K9/033 , G06K9/6256 , G06K9/6267 , G06T7/0004 , G06T7/001 , G06T2207/30148
摘要： A method for classification includes receiving inspection data associated with a plurality of defects found in one or more samples and receiving one or more benchmark classification comprising a class for each of the plurality of defects. A readiness criterion for one or more of the classes is evaluated based on the one or more benchmark classification results, wherein the readiness criterion comprises for each class, a suitability of the inspection data for training an automatic defect classifier for the class. A portion of the inspection data is selected corresponding to one or more defects associated with one or more classes that satisfy the readiness criterion. One or more automatic classifiers are trained for the one or more classes that satisfy the readiness criterion using the selected portion of the inspection data.

8. 发明授权

US09595091B2 Defect classification using topographical attributes 有权
标题翻译：使用地形属性进行缺陷分类
公开(公告)号：US09595091B2
公开(公告)日：2017-03-14
申请号：US13451490
申请日：2012-04-19
申请人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
发明人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06T7/0004 , G06T2207/10061 , G06T2207/30148
摘要： A method for classification includes receiving an image of an area of a semiconductor wafer on which a pattern has been formed, the area containing a location of interest. At least one value for one or more attributes of the location of interest are computed based upon topographical features of the location of interest in a three-dimensional (3D) map of the area.
摘要翻译：一种用于分类的方法包括接收其上形成有图案的半导体晶片的区域的图像，该区域包含感兴趣的位置。基于感兴趣位置的一个或多个属性的至少一个值基于该区域的三维（3D）地图中的感兴趣位置的地形特征来计算。

9. 发明申请

US20130279791A1 DEFECT CLASSIFICATION USING TOPOGRAPHICAL ATTRIBUTES 有权
标题翻译：使用地形属性进行缺陷分类
公开(公告)号：US20130279791A1
公开(公告)日：2013-10-24
申请号：US13451490
申请日：2012-04-19
申请人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
发明人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
IPC分类号： G06K9/00
CPC分类号： G06T7/0004 , G06T2207/10061 , G06T2207/30148
摘要： A method for classification includes receiving an image of an area of a semiconductor wafer on which a pattern has been formed, the area containing a location of interest. At least one value for one or more attributes of the location of interest are computed based upon topographical features of the location of interest in a three-dimensional (3D) map of the area.
摘要翻译：一种用于分类的方法包括接收其上形成有图案的半导体晶片的区域的图像，该区域包含感兴趣的位置。基于感兴趣位置的一个或多个属性的至少一个值基于该区域的三维（3D）地图中的感兴趣位置的地形特征来计算。

10. 发明授权

US09858658B2 Defect classification using CAD-based context attributes 有权
公开(公告)号：US09858658B2
公开(公告)日：2018-01-02
申请号：US13451486
申请日：2012-04-19
申请人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
发明人： Idan Kaizerman , Ishai Schwarzband , Efrat Rozenman
IPC分类号： G06T7/00
CPC分类号： G06T7/001 , G06T2207/10061 , G06T2207/30148
摘要： A method for classification includes receiving an image of an area of a semiconductor wafer on which a pattern has been formed, the area containing an image location of interest, and receiving computer-aided design (CAD) data relating to the pattern comprising a CAD location of interest corresponding to the image location of interest. At least one value for one or more attributes of the image location of interest is computed based on a context of the CAD location of interest with respect to the CAD data.

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