Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020118126 - SYSTEM AND METHOD FOR DIFFERENCE FILTER AND APERTURE SELECTION USING SHALLOW DEEP LEARNING

Publication Number WO/2020/118126
Publication Date 11.06.2020
International Application No. PCT/US2019/064807
International Filing Date 06.12.2019
IPC
G06T 7/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
G06T 5/20 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
5Image enhancement or restoration
20by the use of local operators
G06T 7/11 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
10Segmentation; Edge detection
11Region-based segmentation
CPC
G01N 2223/646
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
2223Investigating materials by wave or particle radiation
60Specific applications or type of materials
646flaws, defects
G01N 23/2251
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
23Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00G01N17/00, G01N21/00 or G01N22/00
22by measuring secondary emission from the material
225using electron or ion
2251using incident electron beams, e.g. scanning electron microscopy [SEM]
G06K 9/6253
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6253User interactive design
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6262
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6262Validation, performance evaluation or active pattern learning techniques
G06K 9/6267
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
Applicants
  • KLA CORPORATION [US]/[US]
Inventors
  • BHATTACHARYYA, Santosh
  • GEORGE, Jacob
  • PARAMASIVAM, Saravanan
  • PLIHAL, Martin
Agents
  • MCANDREWS, Kevin
  • MORRIS, Elizabeth M.N
Priority Data
16/277,76915.02.2019US
20184104636107.12.2018IN
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEM AND METHOD FOR DIFFERENCE FILTER AND APERTURE SELECTION USING SHALLOW DEEP LEARNING
(FR) SYSTÈME ET PROCÉDÉ DE SÉLECTION D'OUVERTURE ET DE FILTRE DE DIFFÉRENCE À L'AIDE D'UN APPRENTISSAGE PEU PROFOND
Abstract
(EN)
A system for defect review and classification is disclosed. The system may include a controller, wherein the controller may be configured to receive one or more training images of a specimen. The one or more training images including a plurality of training defects. The controller may be further configured to apply a plurality of difference filters to the one or more training images, and receive a signal indicative of a classification of a difference filter effectiveness metric for at least a portion of the plurality of difference filters. The controller may be further configured to generate a deep learning network classifier based on the received classification and the attributes of the plurality of training defects. The controller may be further configured to extract convolution layer filters of the deep learning network classifier, and generate one or more difference filter recipes based on the extracted convolution layer filters.
(FR)
La présente invention concerne un système d'analyse et de classification de défauts. Le système peut comprendre un contrôleur, le contrôleur pouvant être configuré pour recevoir une ou plusieurs images d'apprentissage d'un spécimen. Lesdites images d'apprentissage comprennent une pluralité de défauts d'apprentissage. Le contrôleur peut en outre être configuré pour appliquer une pluralité de filtres de différence auxdites mages d'apprentissage, et recevoir un signal indicatif d'une classification d'une métrique d'efficacité de filtre de différence pour au moins une partie de la pluralité de filtres de différence. Le contrôleur peut en outre être configuré pour générer un classificateur de réseau d'apprentissage profond sur la base de la classification reçue et des attributs de la pluralité de défauts d'apprentissage. Le contrôleur peut en outre être configuré pour extraire des filtres de couche de convolution du classificateur de réseau d'apprentissage profond, et générer une ou plusieurs recettes de filtre de différence sur la base des filtres de couche de convolution extraits.
Latest bibliographic data on file with the International Bureau