公开(公告)号：US20250071419A1

公开(公告)日：2025-02-27

申请号：US18793931

申请日：2024-08-04

Applicant: KLA Corporation

Inventor： Raghavan Konuru ,  Jeetsagar Ghorai ,  Jacob George ,  Niveditha LakshmiNarasimhan ,  Sairam Ravu ,  Saravanan Paramasivam ,  Martin Plihal ,  Prasanti Uppaluri

IPC: H04N23/667

Abstract: Methods and systems for selecting modes for a mode selection process are provided. One system includes a computer subsystem configured for determining information for a specimen and at least one value of a characteristic of the information from images generated for the specimen with an initial subset of different modes of an imaging subsystem. The computer subsystem is also configured for predicting probabilities that better values of the characteristic are determined from the images generated with the different modes other than the initial subset based on the determined at least one value of the characteristic and a relationship between the different modes and associated values of the characteristic of the information. In addition, the computer subsystem is configured for selecting an additional subset of the different modes for which the generating and determining steps are performed next by the imaging and computer subsystems, respectively, based on the predicted probabilities.

公开(公告)号：US20210027445A1

公开(公告)日：2021-01-28

申请号：US16935159

申请日：2020-07-21

Applicant: KLA Corporation

Inventor： Martin Plihal ,  Saravanan Paramasivam ,  Jacob George ,  Niveditha Lakshmi Narasimhan ,  Sairam Ravu ,  Somesh Challapalli ,  Prasanti Uppaluri

IPC: G06T7/00 ,  G06K9/62 ,  G06N20/00

Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images a specimen, and a controller communicatively coupled to the characterization sub-system. The controller may be configured to: receive from the characterization sub-system one or more training images of one or more defects of a training specimen; generate one or more augmented images of the one or more defects of the training specimen; generate a machine learning classifier based on the one or more augmented images of the one or more defects of the training specimen; receive from the characterization sub-system one or more target images of one or more target features of a target specimen; and determine one or more defects of the one or more target features with the machine learning classifier.

公开(公告)号：US11676264B2

公开(公告)日：2023-06-13

申请号：US16935159

申请日：2020-07-21

Applicant: KLA Corporation

Inventor： Martin Plihal ,  Saravanan Paramasivam ,  Jacob George ,  Niveditha Lakshmi Narasimhan ,  Sairam Ravu ,  Somesh Challapalli ,  Prasanti Uppaluri

IPC: G06T7/00 ,  G06N20/00 ,  G06F18/214 ,  G06F18/21 ,  G06V20/69

CPC classification number: G06T7/001 ,  G06F18/214 ,  G06F18/217 ,  G06N20/00 ,  G06V20/69 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148

Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images a specimen, and a controller communicatively coupled to the characterization sub-system. The controller may be configured to: receive from the characterization sub-system one or more training images of one or more defects of a training specimen; generate one or more augmented images of the one or more defects of the training specimen; generate a machine learning classifier based on the one or more augmented images of the one or more defects of the training specimen; receive from the characterization sub-system one or more target images of one or more target features of a target specimen; and determine one or more defects of the one or more target features with the machine learning classifier.

公开(公告)号：US11379967B2

公开(公告)日：2022-07-05

申请号：US16744385

申请日：2020-01-16

Applicant: KLA Corporation

Inventor： Jacob George ,  Saravanan Paramasivam ,  Martin Plihal ,  Niveditha Lakshmi Narasimhan ,  Sairam Ravu ,  Prasanti Uppaluri

IPC: G06T7/00 ,  G06N3/08 ,  G06K9/62

Abstract: Methods and systems for improved detection and classification of defects of interest (DOI) is realized based on values of one or more automatically generated attributes derived from images of a candidate defect. Automatically generated attributes are determined by iteratively training, reducing, and retraining a deep learning model. The deep learning model relates optical images of candidate defects to a known classification of those defects. After model reduction, attributes of the reduced model are identified which strongly relate the optical images of candidate defects to the known classification of the defects. The reduced model is subsequently employed to generate values of the identified attributes associated with images of candidate defects having unknown classification. In another aspect, a statistical classifier is employed to classify defects based on automatically generated attributes and attributes identified manually.

公开(公告)号：US20200234428A1

公开(公告)日：2020-07-23

申请号：US16744385

申请日：2020-01-16

Applicant: KLA Corporation

Inventor： Jacob George ,  Saravanan Paramasivam ,  Martin Plihal ,  Niveditha Lakshmi Narasimhan ,  Sairam Ravu ,  Prasanti Uppaluri

IPC: G06T7/00 ,  G06N3/08 ,  G06K9/62

Abstract: Methods and systems for improved detection and classification of defects of interest (DOI) is realized based on values of one or more automatically generated attributes derived from images of a candidate defect. Automatically generated attributes are determined by iteratively training, reducing, and retraining a deep learning model. The deep learning model relates optical images of candidate defects to a known classification of those defects. After model reduction, attributes of the reduced model are identified which strongly relate the optical images of candidate defects to the known classification of the defects. The reduced model is subsequently employed to generate values of the identified attributes associated with images of candidate defects having unknown classification. In another aspect, a statistical classifier is employed to classify defects based on automatically generated attributes and attributes identified manually.