Method of deep learning-based examination of a semiconductor specimen and system thereof

    公开(公告)号:US11205119B2

    公开(公告)日:2021-12-21

    申请号:US15384058

    申请日:2016-12-19

    Abstract: There are provided system and method of examining a semiconductor specimen. The method comprises: upon obtaining a Deep Neural Network (DNN) trained for a given examination-related application within a semiconductor fabrication process, processing together one or more fabrication process (FP) images using the obtained trained DNN, wherein the DNN is trained using a training set comprising ground truth data specific for the given application; and obtaining examination-related data specific for the given application and characterizing at least one of the processed one or more FP images. The examination-related application can be, for example, classifying at least one defect presented by at least one FP image, segmenting the at least one FP image, detecting defects in the specimen presented by the at least one FP image, registering between at least two FP images, regression application enabling reconstructing the at least one FP image in correspondence with different examination modality, etc.

    Method of defect classification and system thereof

    公开(公告)号:US10748271B2

    公开(公告)日:2020-08-18

    申请号:US15962909

    申请日:2018-04-25

    Abstract: There are provided system and method of classifying defects in a specimen. The method includes: obtaining one or more defect clusters detected on a defect map of the specimen, each cluster characterized by a set of cluster attributes comprising spatial attributes including spatial density indicative of density of defects in one or more regions accommodating the cluster, each given defect cluster being detected at least based on the spatial density thereof meeting a criterion; for each cluster, applying a cluster classifier to a respective set of cluster attributes thereof to associate the cluster with one or more labels of a predefined set of labels, wherein the cluster classifier is trained using cluster training data; and identifying DOI in each cluster by performing a defect filtration for each cluster using one or more filtering parameters specified in accordance with the label of the cluster.

    ITERATIVE DEFECT FILTERING PROCESS
    4.
    发明申请

    公开(公告)号:US20190012781A1

    公开(公告)日:2019-01-10

    申请号:US16102112

    申请日:2018-08-13

    Abstract: Data indicative of a group of defect candidates may be obtained. The data may be indicative of a group of defect candidates and may include values of attributes for each defect candidate of the group of defect candidates. Sub-groups of defect candidates may be iteratively selected for review using a review recipe to classify the defect candidates in each selected sub-group based on the values of attributes of respective defect candidates and classification results of previously reviewed defect candidates. The sub-groups may be selected until a sampling stop condition is fulfilled to obtain a classification output for the wafer. Instructions specifying at least one of the sampling stop condition, the inspection recipe, or the review recipe may be altered and additional defect candidates in a next wafer may be classified by using the altered instructions.

    Method of defect classification and system thereof

    公开(公告)号:US11526979B2

    公开(公告)日:2022-12-13

    申请号:US16993869

    申请日:2020-08-14

    Abstract: There are provided system and method of classifying defects in a specimen. The method includes: obtaining one or more defect clusters detected on a defect map of the specimen, each cluster characterized by a set of cluster attributes comprising spatial attributes including spatial density indicative of density of defects in one or more regions accommodating the cluster, each given defect cluster being detected at least based on the spatial density thereof meeting a criterion. The defect map also comprises non-clustered defects. Defects of interest (DOI) are identified in each cluster by performing respective defect filtrations for each cluster and non-clustered defects.

    Process window analysis
    8.
    发明授权

    公开(公告)号:US10312161B2

    公开(公告)日:2019-06-04

    申请号:US14666183

    申请日:2015-03-23

    Abstract: A method for process analysis includes acquiring first inspection data, using a first inspection modality, with respect to a substrate having multiple instances of a predefined pattern of features formed thereon using different, respective sets of process parameters. Characteristics of defects identified in the first inspection data are processed so as to select a first set of defect locations in which the first inspection data are indicative of an influence of the process parameters on the defects. Second inspection data are acquired, using a second inspection modality having a finer resolution than the first inspection modality, of the substrate at the locations in the first set. The defects appearing in the second inspection data are analyzed so as to select, from within the first set of the locations, a second set of the locations in which the second inspection data are indicative of an optimal range of the process parameters.

    Iterative defect filtering process
    10.
    发明授权

    公开(公告)号:US10049441B2

    公开(公告)日:2018-08-14

    申请号:US15019894

    申请日:2016-02-09

    Abstract: A method for classifying defects of a wafer, the method is executed by a computerized system, the method may include obtaining defect candidate information about a group of defect candidates, wherein the defect candidate information comprises values of attributes per each defect candidate of the group; selecting, by a processor of the computerized system, a selected sub-group of defect candidates in response to values of attributes of defect candidates that belong to at least the selected sub-group; classifying defect candidates of the selected sub-group to provide selected sub-group classification results; repeating, until fulfilling a stop condition: selecting an additional selected sub-group of defect candidates in response to (a) values of attributes of defect candidates that belong to at least the additional selected sub-group; and (b) classification results obtained from classifying at least one other selected sub-group; and classifying defect candidates of the additional selected sub-group to provide additional selected sub-group classification results.

Patent Agency Ranking