WO2017204519A3 - 데이터 밸런싱을 통한 학습기반의 비전검사 방법 및 이를 이용한 데이터 밸런싱을 통한 학습기반의 비전검사 장치 - Google Patents

데이터 밸런싱을 통한 학습기반의 비전검사 방법 및 이를 이용한 데이터 밸런싱을 통한 학습기반의 비전검사 장치 Download PDF

Info

Publication number
WO2017204519A3
WO2017204519A3 PCT/KR2017/005326 KR2017005326W WO2017204519A3 WO 2017204519 A3 WO2017204519 A3 WO 2017204519A3 KR 2017005326 W KR2017005326 W KR 2017005326W WO 2017204519 A3 WO2017204519 A3 WO 2017204519A3
Authority
WO
WIPO (PCT)
Prior art keywords
data
vision inspection
inspection method
based learning
inspected
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/KR2017/005326
Other languages
English (en)
French (fr)
Other versions
WO2017204519A2 (ko
Inventor
오병준
전동철
신원종
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anicoltd
Original Assignee
Anicoltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anicoltd filed Critical Anicoltd
Priority to CN201780001010.9A priority Critical patent/CN109462999B/zh
Publication of WO2017204519A2 publication Critical patent/WO2017204519A2/ko
Publication of WO2017204519A3 publication Critical patent/WO2017204519A3/ko
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8806—Specially adapted optical and illumination features
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/0008—Industrial image inspection checking presence/absence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8806—Specially adapted optical and illumination features
    • G01N2021/8809—Adjustment for highlighting flaws
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Chemical & Material Sciences (AREA)
  • Quality & Reliability (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • Software Systems (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

본 발명의 데이터 밸런싱을 통한 학습기반의 비전검사 방법은 진성불량품의 샘플인 진성표본 및 가성불량품의 샘플인 가성표본으로부터 영상이미지가 수집되어 수식화되고, 특징공간상에 도식화되어 진성데이터가 위치한 영역 및 가성데이터가 위치한 영역의 경계인 분류기준을 도출하는 사전학습 단계, 검사대상물로부터 영상이미지로 추출되어 수식화된 피검데이터를 특징공간상에 대입하고 분류기준을 경계로 특징공간상에서 피검데이터가 위치하는 영역을 판단하여 검사대상물을 진성불량 또는 가성불량으로 판단하는 불량판별 단계 및 사전학습 단계에 피검데이터를 적용하여 특징공간상의 분류기준을 수정하되, 피검데이터는 진성데이터 및 가성데이터가 동일한 수로 구성되도록 데이터 밸런싱 단계를 통해 보정되는 추가학습 단계를 포함하고, 불량판별 단계 및 추가학습 단계가 반복 수행된다.
PCT/KR2017/005326 2016-05-23 2017-05-23 데이터 밸런싱을 통한 학습기반의 비전검사 방법 및 이를 이용한 데이터 밸런싱을 통한 학습기반의 비전검사 장치 Ceased WO2017204519A2 (ko)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201780001010.9A CN109462999B (zh) 2016-05-23 2017-05-23 通过数据平衡基于学习的视觉检查方法以及利用其的视觉检查装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020160062783A KR101782363B1 (ko) 2016-05-23 2016-05-23 데이터 밸런싱을 통한 학습기반의 비전검사 방법
KR10-2016-0062783 2016-05-23

Publications (2)

Publication Number Publication Date
WO2017204519A2 WO2017204519A2 (ko) 2017-11-30
WO2017204519A3 true WO2017204519A3 (ko) 2018-08-09

Family

ID=60036118

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2017/005326 Ceased WO2017204519A2 (ko) 2016-05-23 2017-05-23 데이터 밸런싱을 통한 학습기반의 비전검사 방법 및 이를 이용한 데이터 밸런싱을 통한 학습기반의 비전검사 장치

Country Status (3)

Country Link
KR (1) KR101782363B1 (ko)
CN (1) CN109462999B (ko)
WO (1) WO2017204519A2 (ko)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111819598B (zh) * 2018-04-26 2023-06-13 大王制纸株式会社 分选装置、分选方法以及分选程序和计算机可读取的记录介质或存储设备
KR20200039047A (ko) 2018-10-01 2020-04-16 에스케이씨 주식회사 필름 결함 검출 방법 및 시스템
KR102209505B1 (ko) * 2018-12-13 2021-02-01 재단법인대구경북과학기술원 데이터 빈도수 분석을 통한 인공지능 학습 방법 및 장치
KR102223070B1 (ko) * 2019-01-23 2021-03-05 한국과학기술원 신경망 학습 방법 및 장치
KR102958845B1 (ko) 2022-11-24 2026-04-30 부산대학교 산학협력단 심층 학습 기반의 표면 검사를 이용한 불량 탐지를 위한 장치 및 방법
CN116484262B (zh) * 2023-05-06 2023-12-08 南通大学 一种基于文本分类对纺织设备故障辅助处理方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0743126A (ja) * 1993-08-02 1995-02-10 Nikon Corp パターン検査装置
JP2002174603A (ja) * 2000-12-08 2002-06-21 Olympus Optical Co Ltd 欠陥分類方法
JP3756507B1 (ja) * 2004-09-17 2006-03-15 シャープ株式会社 画像処理アルゴリズム評価方法および装置、画像処理アルゴリズム生成方法および装置、プログラムならびにプログラム記録媒体
JP2006292615A (ja) * 2005-04-13 2006-10-26 Sharp Corp 外観検査装置、外観検査方法、コンピュータを外観検査装置として機能させるためのプログラムおよび記録媒体
KR20100068734A (ko) * 2008-12-15 2010-06-24 (주)워프비전 인쇄회로기판의 불량 확인방법

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001041068A1 (fr) * 1999-11-29 2001-06-07 Olympus Optical Co., Ltd. Systeme de detection de defaut
JP4504612B2 (ja) * 2002-08-12 2010-07-14 株式会社日立ハイテクノロジーズ 異物検査方法及び異物検査装置
US20090175514A1 (en) * 2004-11-19 2009-07-09 Koninklijke Philips Electronics, N.V. Stratification method for overcoming unbalanced case numbers in computer-aided lung nodule false positive reduction
CN101140619A (zh) * 2006-09-05 2008-03-12 大日本网目版制造株式会社 图像处理装置、数据处理装置及参数调整方法
US9219886B2 (en) * 2012-12-17 2015-12-22 Emerson Electric Co. Method and apparatus for analyzing image data generated during underground boring or inspection activities
KR20150095053A (ko) * 2014-02-12 2015-08-20 한화테크윈 주식회사 제품 검사의 유효성 검증 장치 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0743126A (ja) * 1993-08-02 1995-02-10 Nikon Corp パターン検査装置
JP2002174603A (ja) * 2000-12-08 2002-06-21 Olympus Optical Co Ltd 欠陥分類方法
JP3756507B1 (ja) * 2004-09-17 2006-03-15 シャープ株式会社 画像処理アルゴリズム評価方法および装置、画像処理アルゴリズム生成方法および装置、プログラムならびにプログラム記録媒体
JP2006292615A (ja) * 2005-04-13 2006-10-26 Sharp Corp 外観検査装置、外観検査方法、コンピュータを外観検査装置として機能させるためのプログラムおよび記録媒体
KR20100068734A (ko) * 2008-12-15 2010-06-24 (주)워프비전 인쇄회로기판의 불량 확인방법

Also Published As

Publication number Publication date
CN109462999B (zh) 2021-05-07
WO2017204519A2 (ko) 2017-11-30
KR101782363B1 (ko) 2017-09-27
CN109462999A (zh) 2019-03-12

Similar Documents

Publication Publication Date Title
MX2020006757A (es) Sistema y metodo para la configuracion de la inspeccion de la linea de produccion.
MX2024015892A (es) Sistemas y metodos para determinar defectos en objetos fisicos
BR112018009108A2 (pt) método para a aquisição e análise de imagens aéreas
GB2554361A8 (en) Automatic image based object damage assessment
MX345972B (es) Sistema, métodos y dispositivo de análisis de material.
TW201614586A (en) Repeater detection
WO2018046957A3 (en) A reading system, text display method and apparatus
CA2771868C (en) Method for real time detection of defects in a food product
WO2007079344A3 (en) Methods and systems for binning defects detected on a specimen
MX360696B (es) Dispositivo y método de inspección de defectos superficiales para chapas de acero revestidas por inmersión en caliente.
MX2018001181A (es) Sistema y metodo para facilitar software de soldadura como un servicio.
SG10201705823YA (en) Apparatus And Method For Monitoring Preparation Of A Food Product
MX373243B (es) Metodo, sistema y aparato para asignar tareas de interpretacion de imagenes.
EP4235598A3 (en) System and method for real time assay monitoring
ZA201806995B (en) Break analysis apparatus and method
IL244028B (en) Adaptive local thresholding and color filtering
JP2016020867A5 (ko)
WO2018087338A3 (de) Inspektionsverfahren und inspektionssystem zum inspizieren eines fahrzeugs im betriebszustand
EP3236418A3 (en) Image processing apparatus, image processing method, and storage medium
WO2011128880A3 (en) Method and apparatus for visual search stability
MY189727A (en) Method of detecting defects of a moving sheet of flexible fibrous material
IN2014DN10148A (ko)
HK1246401A1 (zh) 用於显微镜的方法及设备
EP2999956A1 (en) Method for the surface inspection of long products and apparatus suitable for carrying out such a method
IL262454A (en) Optimizing defect detection in an automatic visual inspection process

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17803038

Country of ref document: EP

Kind code of ref document: A2

122 Ep: pct application non-entry in european phase

Ref document number: 17803038

Country of ref document: EP

Kind code of ref document: A2