公开(公告)号：KR20180071405A

公开(公告)日：2018-06-27

申请号：KR20187017048

申请日：2016-11-17

Applicant: KLA TENCOR CORP

Inventor： BHASKAR KRIS ,  JORDAN III JOHN R ,  KARSENTI LAURENT ,  VENKATARAMAN SANKAR ,  CARMON YAIR

IPC: G01N21/88 ,  G01N21/956

CPC classification number: G06T7/0004 ,  G06K9/4642 ,  G06K9/6256 ,  G06K9/6269 ,  G06K9/6287 ,  G06T7/0079 ,  G06T2207/10061 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148

Abstract: 시편상의결함을검출하기위한방법및 시스템이제공된다. 하나의시스템은생성모델을포함한다. 생성모델은입력특징맵 볼륨의픽셀블록을레이블에매핑하도록구성된비선형네트워크를포함한다. 레이블은블록의하나이상의결함관련특성들을나타낸다. 시스템은하나의테스트이미지를생성모델에입력하며, 이모델은단일의테스트이미지내 픽셀블록의특징을결정하고매핑에기초하여블록에대한레이블을결정한다. 시스템은결정된레이블에기초하여시편의결함을검출한다.

公开(公告)号：KR20180071404A

公开(公告)日：2018-06-27

申请号：KR20187017023

申请日：2016-11-16

Applicant: KLA TENCOR CORP

Inventor： MAHER CHRISTOPHER ,  BRAUER BJORN ,  RAMACHANDRAN VIJAY ,  KARSENTI LAURENT ,  ROSENGAUS ELIEZER ,  JORDAN JOHN ,  MILLER RONI

IPC: G06T7/00 ,  G01N21/17 ,  G01N21/88

CPC classification number: G06T7/001 ,  G06K9/6202 ,  G06K9/6212 ,  G06K9/74 ,  G06T7/11 ,  G06T2207/20182 ,  G06T2207/30148

Abstract: 결함검출방법은, 기준이미지를획득하는것; 기준이미지의타겟영역을선택하는것; 매칭메트릭에기초하여, 타겟영역에대응하는기준이미지의하나이상의비교영역을식별하는것; 테스트이미지를획득하는것; 기준이미지의타겟영역및 기준이미지의하나이상의비교영역으로테스트이미지를마스킹하는것; 테스트이미지의하나이상의비교영역에기초하여테스트이미지의타겟영역에대한결함임계치를정의하는것; 및결함임계치에기초하여테스트이미지의타겟영역이결함을포함하는지의여부를결정하는것을포함한다.

公开(公告)号：SG11201803667RA

公开(公告)日：2018-06-28

申请号：SG11201803667R

申请日：2016-11-16

Applicant: KLA TENCOR CORP

Inventor： MAHER CHRISTOPHER ,  BRAUER BJORN ,  RAMACHANDRAN VIJAY ,  KARSENTI LAURENT ,  ROSENGAUS ELIEZER ,  JORDAN JOHN ,  MILLER RONI

IPC: G06T7/00 ,  G01N21/17 ,  G01N21/88

Abstract: A defect detection method includes acquiring a reference image; selecting a target region of the reference image; identifying, based on a matching metric, one or more comparative regions of the reference image corresponding to the target region; acquiring a test image; masking the test image with the target region of the reference image and the one or more comparative regions of the reference image; defining a defect threshold for the target region in the test image based on the one or more comparative regions in the test image; and determining whether the target region of the test image contains a defect based on the defect threshold.

公开(公告)号：SG11201703581XA

公开(公告)日：2017-06-29

申请号：SG11201703581X

申请日：2015-11-23

Applicant: KLA TENCOR CORP

Inventor： KARSENTI LAURENT ,  BHASKAR KRIS ,  WAGNER MARK ,  DUFFY BRIAN ,  RAMACHANDRAN VIJAYAKUMAR

IPC: G01R31/26 ,  G01R31/01 ,  G01R31/28

Abstract: The invention discloses a method and system for displaying electronic information for an Online Dating Service. Information is received through a variety of means including electronic analysis of photographs and communications as well as direct questions posed to an individual. Once the information is received a profile describing the interest, personality traits and what traits the individual looks for in a companion is created. To prevent priming based on physical appearance the word cloud is displayed to other individuals prior to a photograph. The photograph can be revealed to the other individuals if they take affirmative action to view the photograph or after an arbitrary period of time such that the other individuals can be primed based on the information in the word cloud without losing the emotional investment in finding a companion.

公开(公告)号：SG11201803666WA

公开(公告)日：2018-06-28

申请号：SG11201803666W

申请日：2016-11-17

Applicant: KLA TENCOR CORP

Inventor： BHASKAR KRIS ,  JORDAN III JOHN R ,  KARSENTI LAURENT ,  VENKATARAMAN SANKAR ,  CARMON YAIR

IPC: G01N21/88

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.