中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

33 records (took 0.021 seconds)

    INSPECTION OF RETICLES USING MACHINE LEARNING
    1.
    发明申请
    INSPECTION OF RETICLES USING MACHINE LEARNING 审中-公开

    公开(公告)号：US20190206041A1

    公开(公告)日：2019-07-04

    申请号：US16201788

    申请日：2018-11-27

    Applicant: KLA-Tencor Corporation

    Inventor： Hawren Fang ,  Abdurrahman Sezginer ,  Rui-fang Shi

    IPC: G06T7/00

    CPC classification number: G06T7/001 ,  G06T2207/20081 ,  G06T2207/20084

    Abstract: Disclosed are methods and apparatus for inspecting a photolithographic reticle. A near field reticle image is generated via a deep learning process based on a reticle database image produced from a design database, and a far field reticle image is simulated at an image plane of an inspection system via a physics-based process based on the near field reticle image. The deep learning process includes training a deep learning model based on minimizing differences between the far field reticle images and a plurality of corresponding training reticle images acquired by imaging a training reticle fabricated from the design database, and such training reticle images are selected for pattern variety and are defect-free. A test area of a test reticle, which is fabricated from the design database, is inspected for defects via a die-to-database process that includes comparing a plurality of references images from a reference far field reticle image to a plurality of test images acquired by the inspection system from the test reticle. The reference far field reticle image is simulated based on a reference near field reticle image that is generated by the trained deep learning model.

    Apparatus and methods for predicting wafer-level defect printability
    2.
    发明授权
    Apparatus and methods for predicting wafer-level defect printability 有权

    公开(公告)号：US10304180B2

    公开(公告)日：2019-05-28

    申请号：US15641150

    申请日：2017-07-03

    Applicant: KLA-Tencor Corporation

    Inventor： Rui-fang Shi ,  Abdurrahman Sezginer

    IPC: G06T7/00 ,  G01N21/956 ,  G03F1/84 ,  G03F7/20

    Abstract: Disclosed are methods and apparatus for qualifying a photolithographic reticle. A reticle inspection tool is used to acquire images at different imaging configurations from each of a plurality of pattern areas of a test reticle. A reticle near field for each of the pattern areas of the test reticle is recovered based on the acquired images from each pattern area of the test reticle. A lithography model is applied to the reticle near field for the test reticle to simulate a plurality of test wafer images, and the simulated test wafer images are analyzed to determine whether the test reticle will likely result in an unstable or defective wafer.

    Using reflected and transmission maps to detect reticle degradation
    6.
    发明授权
    Using reflected and transmission maps to detect reticle degradation 有权
    使用反射和透射图来检测光栅退化

    公开(公告)号：US09417191B2

    公开(公告)日：2016-08-16

    申请号：US14381304

    申请日：2013-03-07

    Applicant: KLA-Tencor Corporation

    Inventor： Carl E. Hess ,  Rui-fang Shi

    IPC: G01N21/00 ,  G01N21/95 ,  G03F1/84 ,  G01M11/00 ,  G01N21/956

    CPC classification number: G01N21/95 ,  G01M11/00 ,  G01N21/95607 ,  G01N2021/9511 ,  G01N2021/95676 ,  G01N2201/06113 ,  G01N2201/062 ,  G01N2201/10 ,  G03F1/84

    Abstract: An optical reticle inspection tool is used during an inspection to obtain, for each local area, an average of multiple reflected intensity values corresponding to light reflected from a plurality of sub-areas of each local area of the reticle. The optical reticle inspection tool is also used during the inspection to obtain, for each local area, an average of multiple transmitted intensity values corresponding to light transmitted through the sub-areas of each local area of the reticle. A combined intensity map is generated by combining, for each local area, the average of multiple reflected intensity values and the average of multiple transmitted intensity values such that a reticle pattern of the reticle is cancelled from the combined intensity map if the reticle has not degraded and such that the reticle pattern of the reticle is not cancelled out of the combined intensity map if the reticle has degraded.

    Abstract translation: 在检查期间使用光学掩模版检查工具，以针对每个局部区域获得对应于从掩模版的每个局部区域的多个子区域反射的光的多个反射强度值的平均值。 在检查期间还使用光学掩模版检查工具，以对于每个局部区域获得对应于透过分划板的每个局部区域的子区域的光的多个透射强度值的平均值。 通过对于每个局部区域组合多个反射强度值的平均值和多个透射强度值的平均值来产生组合强度图，使得如果标线没有退化，则从组合强度图中取消掩模版的掩模版图案 并且如果掩模版已劣化，则掩模版的掩模版图案不会从组合强度图中抵消。

    Detection of thin lines for selective sensitivity during reticle inspection using processed images
    7.
    发明授权
    Detection of thin lines for selective sensitivity during reticle inspection using processed images 有权
    在使用处理图像的掩模版检查期间检测细线以选择灵敏度

    公开(公告)号：US09092847B2

    公开(公告)日：2015-07-28

    申请号：US14475400

    申请日：2014-09-02

    Applicant: KLA-Tencor Corporation

    Inventor： Zhengyu Wang ,  Rui-fang Shi ,  Lih-Huah Yiin ,  Bing Li

    IPC: G06K9/62 ,  G06T7/00 ,  G03F1/84 ,  G01N21/956

    CPC classification number: G06T7/001 ,  G01N2021/95676 ,  G03F1/84 ,  G06T7/13 ,  G06T7/174 ,  G06T2207/10016 ,  G06T2207/10152 ,  G06T2207/20044 ,  G06T2207/20161 ,  G06T2207/20221 ,  G06T2207/30148

    Abstract: A detection method for a spot image based thin line detection is disclosed. The method includes a step for constructing a band limited spot image from a transmitted and reflected optical image of the mask. The spot image is calibrated to reduce noise introduced by the one or more inspection systems. Based on the band limited spot image, a non-printable feature map is generated for the non-printable features and a printable feature map is generated for the printable features. One or more test images of the mask are analyzed to detect defects on such mask. A sensitivity level of defect detection is reduced in areas of the one or more test images defined by the non-printable feature map, as compared with areas of the one or more test images that are not defined by the non-printable features map

    Abstract translation: 公开了一种用于基于点图像的细线检测的检测方法。 该方法包括从掩模的透射和反射光学图像构造带限光斑图像的步骤。 斑点图像被校准以减少由一个或多个检查系统引入的噪声。 基于带限点图像，为不可打印的特征生成不可打印的特征图，并且为可打印特征生成可打印的特征图。 分析掩模的一个或多个测试图像以检测该掩模上的缺陷。 与由不可打印的特征图定义的一个或多个测试图像的区域相比，在由不可打印的特征图定义的一个或多个测试图像的区域中减少了缺陷检测的灵敏度水平

    DETECTION OF THIN LINES FOR SELECTIVE SENSITIVITY DURING RETICLE INSPECTION USING PROCESSED IMAGES
    8.
    发明申请
    DETECTION OF THIN LINES FOR SELECTIVE SENSITIVITY DURING RETICLE INSPECTION USING PROCESSED IMAGES 有权
    使用加工图像检测检验期间选择灵敏度的薄线

    公开(公告)号：US20140369593A1

    公开(公告)日：2014-12-18

    申请号：US14475400

    申请日：2014-09-02

    Applicant: KLA-Tencor Corporation

    Inventor： Zhengyu Wang ,  Rui-fang Shi ,  Lih-Huah Yiin ,  Bing Li

    IPC: G06T7/00 ,  G03F1/84

    CPC classification number: G06T7/001 ,  G01N2021/95676 ,  G03F1/84 ,  G06T7/13 ,  G06T7/174 ,  G06T2207/10016 ,  G06T2207/10152 ,  G06T2207/20044 ,  G06T2207/20161 ,  G06T2207/20221 ,  G06T2207/30148

    Abstract: A detection method for a spot image based thin line detection is disclosed. The method includes a step for constructing a band limited spot image from a transmitted and reflected optical image of the mask. The spot image is calibrated to reduce noise introduced by the one or more inspection systems. Based on the band limited spot image, a non-printable feature map is generated for the non-printable features and a printable feature map is generated for the printable features. One or more test images of the mask are analyzed to detect defects on such mask. A sensitivity level of defect detection is reduced in areas of the one or more test images defined by the non-printable feature map, as compared with areas of the one or more test images that are not defined by the non-printable features map

    Abstract translation: 公开了一种用于基于点图像的细线检测的检测方法。 该方法包括从掩模的透射和反射光学图像构造带限光斑图像的步骤。 斑点图像被校准以减少由一个或多个检查系统引入的噪声。 基于带限点图像，为不可打印的特征生成不可打印的特征图，并且为可打印特征生成可打印的特征图。 分析掩模的一个或多个测试图像以检测该掩模上的缺陷。 与由不可打印的特征图定义的一个或多个测试图像的区域相比，在由不可打印的特征图定义的一个或多个测试图像的区域中减少了缺陷检测的灵敏度水平

    TIME-VARYING INTENSITY MAP GENERATION FOR RETICLES
    9.
    发明申请
    TIME-VARYING INTENSITY MAP GENERATION FOR RETICLES 审中-公开
    时间变化强烈的地图生成的反应

    公开(公告)号：US20130211736A1

    公开(公告)日：2013-08-15

    申请号：US13757103

    申请日：2013-02-01

    Applicant: KLA-Tencor Corporation

    Inventor： Carl E. Hess ,  Rui-fang Shi ,  Thomas Vavul

    IPC: G01N21/95

    CPC classification number: G01N21/95 ,  G01N21/95607 ,  G01N2021/95676 ,  G03F1/84 ,  G03F7/705 ,  G03F7/7065

    Abstract: An optical reticle inspection tool is used during a first inspection to obtain, for each set of one or more patch areas of the reticle, a reference average of multiple reference intensity values corresponding to light measured from sub-areas of each patch area. After using the reticle in photolithography processes, the optical reticle inspection tool is used during a second inspection to obtain, for each set of one or more patch areas, an average of multiple test intensity values corresponding to light measured from the of sub-areas. The first and second inspections use the same tool setup recipe. A difference intensity map is generated, and such map comprises map values that each corresponds to a difference between each average of the test and reference intensity values for each set of one or more patches. The difference intensity map indicates whether the reticle has degraded over time more than a predefined level.

    Abstract translation: 在第一次检查期间使用光学掩模版检查工具，对于每个掩模版的一个或多个贴片区域，获得对应于从每个贴片区域的子区域测量的光的多个基准亮度值的参考平均值。 在光刻工艺中使用掩模版之后，在第二次检查期间使用光学掩模版检查工具，对于每个一个或多个贴片区域，获得对应于从子区域测量的光的多个测试强度值的平均值。 第一次和第二次检查使用相同的工具设置配方。 生成差分强度图，并且这样的图包括映射值，每个映射值对应于每个一个或多个补丁集合的每个测试平均值和参考强度值之间的差值。 差分强度图表示在超过预定义水平的时间内光罩是否已经劣化。

    INSPECTION OF RETICLES USING MACHINE LEARNING
    10.
    发明申请
    INSPECTION OF RETICLES USING MACHINE LEARNING 有权

    公开(公告)号：US20220084179A1

    公开(公告)日：2022-03-17

    申请号：US17456415

    申请日：2021-11-24

    Applicant: KLA-Tencor Corporation

    Inventor： Hawren Fang ,  Abdurrahman Sezginer ,  Rui-fang Shi

    IPC: G06T7/00

    Abstract: Disclosed are methods and apparatus for inspecting a photolithographic reticle. A plurality of reference far field images are simulated by inputting a plurality of reference near field images into a physics-based model, and the plurality of reference near field images are generated by a trained deep learning model from a test portion of the design database that was used to fabricate a test area of a test reticle. The test area of a test reticle, which was fabricated from the design database, is inspected for defects via a die-to-database process that includes comparing the plurality of reference far field reticle images simulated by the physic-based model to a plurality of test images acquired by the inspection system from the test area of the test reticle.

Patent Agency Ranking