Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 27.07.2021 at 12:00 PM CEST
Settings

Settings

Goto Application

1. WO2020141072 - FULLY AUTOMATED SEM SAMPLING SYSTEM FOR E-BEAM IMAGE ENHANCEMENT

Publication Number WO/2020/141072
Publication Date 09.07.2020
International Application No. PCT/EP2019/085720
International Filing Date 17.12.2019
IPC
G06K 9/03 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR 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
03Detection or correction of errors, e.g. by rescanning the pattern
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR 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
CPC
G06K 9/036
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
03Detection or correction of errors, e.g. by rescanning the pattern
036Evaluation of quality of acquired pattern
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
G06T 2207/10061
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10056Microscopic image
10061from scanning electron microscope
G06T 2207/20081
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20081Training; Learning
G06T 2207/30148
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
30Subject of image; Context of image processing
30108Industrial image inspection
30148Semiconductor; IC; Wafer
Applicants
  • ASML NETHERLANDS B.V. [NL]/[NL]
Inventors
  • ZHOU, Wentian
  • YU, Liangjiang
  • WANG, Teng
  • PU, Lingling
  • FANG, Wei
Agents
  • PETERS, John Antoine
Priority Data
62/787,03131.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) FULLY AUTOMATED SEM SAMPLING SYSTEM FOR E-BEAM IMAGE ENHANCEMENT
(FR) SYSTÈME D'ÉCHANTILLONNAGE SEM ENTIÈREMENT AUTOMATISÉ POUR AMÉLIORATION D'IMAGE DE FAISCEAU ÉLECTRONIQUE
Abstract
(EN)
Disclosed herein is a method of automatically obtaining training images to train a machine learning model that improves image quality. The method may comprise analyzing a plurality of patterns of data relating to a layout of a product to identify a plurality of training locations on a sample of the product to use in relation to training the machine learning model. The method may comprise obtaining a first image having a first quality for each of the plurality of training locations, and obtaining a second image having a second quality for each of the plurality of training locations, the second quality being higher than the first quality. The method may comprise using the first image and the second image to train the machine learning model.
(FR)
L'invention concerne un procédé d'obtention automatique d'images d'apprentissage pour entraîner un modèle d'apprentissage machine qui améliore la qualité d'image. Le procédé peut comprendre l'analyse d'une pluralité de combinaisons de données se rapportant à une disposition d'un produit pour identifier une pluralité d'emplacements d'apprentissage sur un échantillon du produit à utiliser en relation avec l'apprentissage du modèle d'apprentissage machine. Le procédé peut comprendre l'obtention d'une première image ayant une première qualité pour chacun de la pluralité d'emplacements d'apprentissage, et l'obtention d'une seconde image ayant une seconde qualité pour chacun de la pluralité d'emplacements d'apprentissage, la seconde qualité étant supérieure à la première qualité. Le procédé peut comprendre l'utilisation de la première image et de la seconde image pour entraîner le modèle d'apprentissage machine.
Also published as
IL284031
KR1020217019393
Latest bibliographic data on file with the International Bureau