-
公开(公告)号：US20190370955A1
公开(公告)日：2019-12-05
申请号：US16424431
申请日：2019-05-28
Applicant: KLA-Tencor Corporation
Inventor： Jing Zhang , Yujie Dong , Brian Duffy , Richard Wallingford , Michael Daino , Kris Bhaskar
Abstract: Methods and systems for performing active learning for defect classifiers are provided. One system includes one or more computer subsystems configured for performing active learning for training a defect classifier. The active learning includes applying an acquisition function to data points for the specimen. The acquisition function selects one or more of the data points based on uncertainty estimations associated with the data points. The active learning also includes acquiring labels for the selected one or more data points and generating a set of labeled data that includes the selected one or more data points and the acquired labels. The computer subsystem(s) are also configured for training the defect classifier using the set of labeled data. The defect classifier is configured for classifying defects detected on the specimen using the images generated by the imaging subsystem.
-
12.发明申请公开(公告)号：US20170307545A1
公开(公告)日：2017-10-26
申请号：US15643333
申请日：2017-07-06
Applicant: KLA-Tencor Corporation
Inventor： Pavel Kolchin , Richard Wallingford , Lisheng Gao , Grace H. Chen , Markus B. Huber , Robert M. Danen
IPC: G01N21/95
CPC classification number: G01N21/9501
Abstract: Disclosed are methods and apparatus for optimizing a mode of an inspection tool. A first image or signal for each of a plurality of first apertures of the inspection tool is obtained, and each first image or signal pertains to a defect area. For each of a plurality of combinations of the first apertures and their first images or signals, a composite image or signal is obtained. Each composite image or signal is analyzed to determine an optimum one of the combinations of the first apertures based on a defect detection characteristic of each composite image. In one aspect, determining an optimum one of the combinations of the first apertures includes selecting a set of one or more individual apertures that result in the highest signal to noise ratio for the defect area, and the method includes setting the optimum combination of the first apertures on the inspection tool and inspecting a sample using such optimum combination of the first apertures.
-
公开(公告)号：US11295438B2
公开(公告)日：2022-04-05
申请号：US16206691
申请日：2018-11-30
Applicant: KLA-Tencor Corporation
Inventor： Jason Z. Lin , Allen Park , Ellis Chang , Richard Wallingford , Songnian Rong , Chetana Bhaskar
IPC: G06T7/00
Abstract: Mixed-mode includes receiving inspection results including one or more images of a selected region of the wafer, the one or more images include one or more wafer die including a set of repeating blocks, the set of repeating blocks a set of repeating cells. In addition, mixed-mode inspection includes adjusting a pixel size of the one or more images to map each cell, block and die to an integer number of pixels. Further, mixed-mode inspection includes comparing a first wafer die to a second wafer die to identify an occurrence of one or more defects in the first or second wafer die, comparing a first block to a second block to identify an occurrence of one or more defects in the first or second blocks and comparing a first cell to a second cell to identify an occurrence of one or more defects in the first or second cells.
-
公开(公告)号：US10402688B2
公开(公告)日：2019-09-03
申请号：US15720272
申请日：2017-09-29
Applicant: KLA-Tencor Corporation
Inventor： Bjorn Brauer , Vijay Ramachandran , Richard Wallingford , Scott Allen Young
Abstract: Systems and methods for providing an augmented input data to a convolutional neural network (CNN) are disclosed. Wafer images are received at a processor. The wafer image is divided into a plurality of references images each associated with a die in the wafer image. Test images are received. A plurality of difference images are created by differences the test images with the reference images. The reference images and difference images are assembled into the augmented input data for the CNN and provided to the CNN.
-
Patent Agency Ranking
公开(公告)号：US10192303B2
公开(公告)日：2019-01-29
申请号：US14076350
申请日：2013-11-11
Applicant: KLA-Tencor Corporation
Inventor： Jason Z. Lin , Allen Park , Ellis Chang , Richard Wallingford , Songnian Rong , Chetana Bhaskar
Abstract: Mixed-mode includes receiving inspection results including one or more images of a selected region of the wafer, the one or more images include one or more wafer die including a set of repeating blocks, the set of repeating blocks a set of repeating cells. In addition, mixed-mode inspection includes adjusting a pixel size of the one or more images to map each cell, block and die to an integer number of pixels. Further, mixed-mode inspection includes comparing a first wafer die to a second wafer die to identify an occurrence of one or more defects in the first or second wafer die, comparing a first block to a second block to identify an occurrence of one or more defects in the first or second blocks and comparing a first cell to a second cell to identify an occurrence of one or more defects in the first or second cells.
-
公开(公告)号：US10132760B2
公开(公告)日：2018-11-20
申请号：US15643333
申请日：2017-07-06
Applicant: KLA-Tencor Corporation
Inventor： Pavel Kolchin , Richard Wallingford , Lisheng Gao , Grace H. Chen , Markus B. Huber , Robert M. Danen
IPC: G01N21/95
Abstract: Disclosed are methods and apparatus for optimizing a mode of an inspection tool. A first image or signal for each of a plurality of first apertures of the inspection tool is obtained, and each first image or signal pertains to a defect area. For each of a plurality of combinations of the first apertures and their first images or signals, a composite image or signal is obtained. Each composite image or signal is analyzed to determine an optimum one of the combinations of the first apertures based on a defect detection characteristic of each composite image. In one aspect, determining an optimum one of the combinations of the first apertures includes selecting a set of one or more individual apertures that result in the highest signal to noise ratio for the defect area, and the method includes setting the optimum combination of the first apertures on the inspection tool and inspecting a sample using such optimum combination of the first apertures.
-
公开(公告)号：US20140153814A1
公开(公告)日：2014-06-05
申请号：US14076350
申请日：2013-11-11
Applicant: KLA-Tencor Corporation
Inventor： Jason Z. Lin , Allen Park , Ellis Chang , Richard Wallingford , Songnian Rong , Chetana Bhaskar
IPC: G06T7/00
CPC classification number: G06T7/001 , G06T2207/30148
Abstract: Mixed-mode includes receiving inspection results including one or more images of a selected region of the wafer, the one or more images include one or more wafer die including a set of repeating blocks, the set of repeating blocks a set of repeating cells. In addition, mixed-mode inspection includes adjusting a pixel size of the one or more images to map each cell, block and die to an integer number of pixels. Further, mixed-mode inspection includes comparing a first wafer die to a second wafer die to identify an occurrence of one or more defects in the first or second wafer die, comparing a first block to a second block to identify an occurrence of one or more defects in the first or second blocks and comparing a first cell to a second cell to identify an occurrence of one or more defects in the first or second cells.
Abstract translation: 混合模式包括接收包括晶片的选定区域的一个或多个图像的检查结果，一个或多个图像包括一个或多个晶片管芯，其包括一组重复块，该组重复块是一组重复的单元。 此外，混合模式检查包括调整一个或多个图像的像素尺寸以将每个单元映射到块，并将其死亡到整数个像素。 此外，混合模式检查包括将第一晶片管芯与第二晶片管芯进行比较，以识别第一或第二晶片管芯中的一个或多个缺陷的发生，将第一块与第二块进行比较以识别一个或多个 第一或第二块中的缺陷，并且将第一细胞与第二细胞进行比较以识别第一或第二细胞中的一个或多个缺陷的发生。
-
公开(公告)号：US09726617B2
公开(公告)日：2017-08-08
申请号：US14075488
申请日：2013-11-08
Applicant: KLA-Tencor Corporation
Inventor： Pavel Kolchin , Richard Wallingford , Lisheng Gao , Grace H. Chen , Markus B. Huber , Robert M. Danen
IPC: G01N21/95
CPC classification number: G01N21/9501
Abstract: Disclosed are methods and apparatus for optimizing a mode of an inspection tool. A first image or signal for each of a plurality of first apertures of the inspection tool is obtained, and each first image or signal pertains to a defect area. For each of a plurality of combinations of the first apertures and their first images or signals, a composite image or signal is obtained. Each composite image or signal is analyzed to determine an optimum one of the combinations of the first apertures based on a defect detection characteristic of each composite image.
-
公开(公告)号：US20170191945A1
公开(公告)日：2017-07-06
申请号：US15357888
申请日：2016-11-21
Applicant: KLA-Tencor Corporation
Inventor： Jing Zhang , Jeremy Nesbitt , Grace Hsiu-Ling Chen , Richard Wallingford
CPC classification number: G01N21/8851 , G01N21/9501 , G01N21/95607 , G01N2021/8883 , G01N2021/8887 , G06T3/4053 , G06T5/003 , G06T7/0006 , G06T7/001 , G06T2207/10004 , G06T2207/10056 , G06T2207/20056 , G06T2207/20076 , G06T2207/20081 , G06T2207/30148
Abstract: An inspection system includes an illumination sub-system, a collection sub-system, and a controller. The illumination sub-system includes an illumination source configured to generate a beam of illumination and a set of illumination optics to direct the beam of illumination to a sample. The a collection sub-system includes a set of collection optics to collect illumination emanating from the sample and a detector configured to receive the collected illumination from the sample. The controller is configured to acquire a test image of the sample, reconstruct the test image to enhance the resolution of the test image, and detect one or more defects on the sample based on the reconstructed test image.
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.025 seconds)
