Training a neural network for defect detection in low resolution images

    公开(公告)号:US10599951B2

    公开(公告)日:2020-03-24

    申请号:US16364140

    申请日:2019-03-25

    Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

    Detecting defects on a wafer with run time use of design data
    2.
    发明授权
    Detecting defects on a wafer with run time use of design data 有权
    使用设计数据运行时间检测晶圆上的缺陷

    公开(公告)号:US09183624B2

    公开(公告)日:2015-11-10

    申请号:US14303602

    申请日:2014-06-13

    CPC classification number: G06T7/001 G06T2207/10061 G06T2207/30148

    Abstract: Methods and systems for detecting defects on a wafer are provided. One method includes creating a searchable database for a design for a wafer, which includes assigning values to different portions of the design based on patterns in the different portions of the design and storing the assigned values in the searchable database. Different portions of the design having substantially the same patterns are assigned the same values in the searchable database. The searchable database is configured such that searching of the database can be synchronized with generation of output for the wafer by one or more detectors of a wafer inspection system. Therefore, as the wafer is being scanned, design information for the output can be determined as fast as the output is generated, which enables multiple, desirable design based inspection capabilities.

    Abstract translation: 提供了用于检测晶片上的缺陷的方法和系统。 一种方法包括创建用于晶片设计的可搜索数据库,其包括基于设计的不同部分中的图案将值设计到设计的不同部分,并将所分配的值存储在可搜索的数据库中。 具有基本上相同图案的设计的不同部分在可搜索数据库中被分配相同的值。 可搜索数据库被配置为使得可以通过晶片检查系统的一个或多个检测器与数据库的搜索同步生成晶片的输出。 因此,当正在扫描晶片时,可以确定输出的设计信息与产生的输出一样快,这样可以实现多种基于设计的检测能力。

    TRAINING A NEURAL NETWORK FOR DEFECT DETECTION IN LOW RESOLUTION IMAGES

    公开(公告)号:US20190303717A1

    公开(公告)日:2019-10-03

    申请号:US16364140

    申请日:2019-03-25

    Abstract: Methods and systems for training a neural network for defect detection in low resolution images are provided. One system includes an inspection tool that includes high and low resolution imaging subsystems and one or more components that include a high resolution neural network and a low resolution neural network. Computer subsystem(s) of the system are configured for generating a training set of defect images. At least one of the defect images is generated synthetically by the high resolution neural network using an image generated by the high resolution imaging subsystem. The computer subsystem(s) are also configured for training the low resolution neural network using the training set of defect images as input. In addition, the computer subsystem(s) are configured for detecting defects on another specimen by inputting the images generated for the other specimen by the low resolution imaging subsystem into the trained low resolution neural network.

    Accelerating semiconductor-related computations using learning based models

    公开(公告)号:US10360477B2

    公开(公告)日:2019-07-23

    申请号:US15402169

    申请日:2017-01-09

    Abstract: Methods and systems for performing one or more functions for a specimen using output simulated for the specimen are provided. One system includes one or more computer subsystems configured for acquiring output generated for a specimen by one or more detectors included in a tool configured to perform a process on the specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a learning based model configured for performing one or more first functions using the acquired output as input to thereby generate simulated output for the specimen. The one or more computer subsystems are also configured for performing one or more second functions for the specimen using the simulated output.

    Generating simulated output for a specimen

    公开(公告)号:US10043261B2

    公开(公告)日:2018-08-07

    申请号:US15402094

    申请日:2017-01-09

    Abstract: Methods and systems for generating simulated output for a specimen are provided. One method includes acquiring information for a specimen with one or more computer systems. The information includes at least one of an actual optical image of the specimen, an actual electron beam image of the specimen, and design data for the specimen. The method also includes inputting the information for the specimen into a learning based model. The learning based model is included in one or more components executed by the one or more computer systems. The learning based model is configured for mapping a triangular relationship between optical images, electron beam images, and design data, and the learning based model applies the triangular relationship to the input to thereby generate simulated images for the specimen.

    Single image detection
    10.
    发明授权

    公开(公告)号:US10186026B2

    公开(公告)日:2019-01-22

    申请号:US15353210

    申请日:2016-11-16

    Abstract: Methods and systems for detecting defects on a specimen are provided. One system includes a generative model. The generative model includes a non-linear network configured for mapping blocks of pixels of an input feature map volume into labels. The labels are indicative of one or more defect-related characteristics of the blocks. The system inputs a single test image into the generative model, which determines features of blocks of pixels in the single test image and determines labels for the blocks based on the mapping. The system detects defects on the specimen based on the determined labels.

Patent Agency Ranking