Industrial defect detection method and system
The invention discloses an industrial defect detection method and system, belongs to the technical field of industrial image processing, and provides a normal feature reconstruction model based on an image level and feature level mask strategy, which can reconstruct normal features according to abno...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
11.08.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The invention discloses an industrial defect detection method and system, belongs to the technical field of industrial image processing, and provides a normal feature reconstruction model based on an image level and feature level mask strategy, which can reconstruct normal features according to abnormal features. In an image level mask strategy, extracting normal and abnormal features from a normal industrial image and an abnormal industrial image constructed based on the normal image, and respectively taking the normal and abnormal features as an input signal and a supervision signal; the difference between the input signal and the supervision signal promotes the model to learn global information so as to guide the reconstruction of the abnormal region. In a feature level mask strategy, after feature extraction is carried out on an abnormal feature map after fusion and compression, part of features of the obtained feature map are masked randomly, and then a missing part is reconstructed so as to emphasize lo |
---|---|
AbstractList | The invention discloses an industrial defect detection method and system, belongs to the technical field of industrial image processing, and provides a normal feature reconstruction model based on an image level and feature level mask strategy, which can reconstruct normal features according to abnormal features. In an image level mask strategy, extracting normal and abnormal features from a normal industrial image and an abnormal industrial image constructed based on the normal image, and respectively taking the normal and abnormal features as an input signal and a supervision signal; the difference between the input signal and the supervision signal promotes the model to learn global information so as to guide the reconstruction of the abnormal region. In a feature level mask strategy, after feature extraction is carried out on an abnormal feature map after fusion and compression, part of features of the obtained feature map are masked randomly, and then a missing part is reconstructed so as to emphasize lo |
Author | JIANG YUXIN SHEN WEIMING CAO YUNKANG |
Author_xml | – fullname: SHEN WEIMING – fullname: JIANG YUXIN – fullname: CAO YUNKANG |
BookMark | eNrjYmDJy89L5WTQ9cxLKS0uKcpMzFFISU1LTS4BUiVAKjM_TyE3tSQjP0UhMS9FobiyuCQ1l4eBNS0xpziVF0pzMyi6uYY4e-imFuTHpxYXJCan5qWWxDv7GRqamVoYGBiaOBoTowYAzP4sCA |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | 一种工业缺陷检测方法及系统 |
ExternalDocumentID | CN116580014A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_CN116580014A3 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 13:58:29 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | Chinese English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_CN116580014A3 |
Notes | Application Number: CN202310570502 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230811&DB=EPODOC&CC=CN&NR=116580014A |
ParticipantIDs | epo_espacenet_CN116580014A |
PublicationCentury | 2000 |
PublicationDate | 20230811 |
PublicationDateYYYYMMDD | 2023-08-11 |
PublicationDate_xml | – month: 08 year: 2023 text: 20230811 day: 11 |
PublicationDecade | 2020 |
PublicationYear | 2023 |
RelatedCompanies | HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY |
RelatedCompanies_xml | – name: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY |
Score | 3.6204054 |
Snippet | The invention discloses an industrial defect detection method and system, belongs to the technical field of industrial image processing, and provides a normal... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
Title | Industrial defect detection method and system |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230811&DB=EPODOC&locale=&CC=CN&NR=116580014A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMU61NEwzsjDVTTFJMdU1MTJP1E0yNkrWTbQ0s7RIAWY_yxTQgL6vn5lHqIlXhGkEE0MWbC8M-JzQcvDhiMAclQzM7yXg8roAMYjlAl5bWayflAkUyrd3C7F1UYP2joHtaQtg3nVxsnUN8Hfxd1ZzdrZ19lPzC7IFnTJjAeoPODIzsIKa0aBz9l3DnEC7UgqQqxQ3QQa2AKBpeSVCDExVGcIMnM6wm9eEGTh8oRPewgzs4BWaycVAQWguLBZh0EXct6GQkgpajwGkSsBrqvIUIFdCKyTmpShATmkWZVB0cw1x9tAFuiAe7t14Zz-EY43FGFjy8vNSJRgUjMzNQJNaBmbJqcBejaFJYqKZRbKZmVGKmZmlYYphkiSDFG5zpPBJSjNwgYIONFJqaCjDwFJSVJoqC6xqS5LkwGEEACaFgP4 |
link.rule.ids | 230,309,786,891,25594,76903 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5qfdSbRkXrK4LkFmxe2-QQxG4aojZpkSi9lSQbUQ9pMRHBX-_sNjVe9LQwC8Pswrez8wa4NHJHe9ZtS2Ums1RT7ydqauiZmjjEsRnCz2HcoR9GJHg076bWtAVvq1oY0Sf0UzRHRERliPdKvNeLxonlidzK8ip9RdL82o9dT6mtY_xP24hdb-AOJ2NvTBVKXRop0YPLu8zY3B64WYN1lKAnTKWnAa9KWfxWKf4ObEyQW1HtQuvrRYIOXU1ek2ArrAPeEmyKDM2sRGKNwnIP1Gbehsxyno-BSyVyqgp5ORJaTgomL7s078OFP4xpoKIEs5_jzmjUCGscQLuYF_khyHqf8KBWj2Q5WjWamSTEzgjRGSGOxrT0CLp_8-n-t3kOnSAOR7PRbXR_DNv8GrnXVNNOoF29f-SnqHar9Ezc1zdTl4Po |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Industrial+defect+detection+method+and+system&rft.inventor=SHEN+WEIMING&rft.inventor=JIANG+YUXIN&rft.inventor=CAO+YUNKANG&rft.date=2023-08-11&rft.externalDBID=A&rft.externalDocID=CN116580014A |