会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明申请
    • INTEGRATION OF AUTOMATIC AND MANUAL DEFECT CLASSIFICATION
    • 自动和手动缺陷分类的整合
    • US20130279794A1
    • 2013-10-24
    • US13451496
    • 2012-04-19
    • Gadi GreenbergIdan KaizermanEfrat Rozenman
    • Gadi GreenbergIdan KaizermanEfrat Rozenman
    • G06K9/00
    • G06T7/001G06K9/033G06K9/6269G06K9/6284G06T2207/10061G06T2207/30148
    • 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.
    • 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。
    • 7. 发明授权
    • Defect detection using gray level signatures
    • 使用灰度级别签名的缺陷检测
    • US06603873B1
    • 2003-08-05
    • US09438577
    • 1999-11-12
    • Naama GordonGadi Greenberg
    • Naama GordonGadi Greenberg
    • G06K903
    • G06T7/0006G01N2021/95676G06T2207/30148
    • A method and apparatus for inspecting isolated features on a reticle is provided wherein the isolated features are analyzed for defects globally as individual, whole features, rather than locally, pixel-by-pixel. In one embodiment, the reticle is imaged to produce pixels having a gray level, and an isolated feature is identified. An energy value for the isolated feature to be inspected is calculated by summing the gray levels of its pixels. A plurality of scatter values for the feature in different directions in the feature is calculated based on the equilibrium center of the feature to produce a unique “signature” for the inspected feature. The energy and scatter values of the inspected feature's signature are then compared with energy and scatter values associated with a corresponding reference feature to determine whether a defect exists in the inspected feature.
    • 提供了用于检查掩模版上的隔离特征的方法和装置,其中分离的特征被全局地分析为单独的,整体特征,而不是逐个像素的局部缺陷。 在一个实施例中,将掩模版成像以产生具有灰度级的像素,并且识别孤立的特征。 通过对其像素的灰度级进行求和来计算要检查的孤立特征的能量值。 基于特征的平衡中心计算特征中不同方向上的特征的多个散射值,以产生用于被检查特征的唯一“签名”。 然后将检查特征的签名的能量和散射值与与相应的参考特征相关联的能量和散射值进行比较,以确定检查特征中是否存在缺陷。