Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122269694> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W3122269694 abstract "Nowadays, automatic optical inspection (AOI) has been widely used in advanced manufactory. In AOI area, crisscross background may influence extraction of defect features. A package, semi-finished product of textile industry, usually has cricross background. This study aims to classify four types of package defects, which are wound-in waste, spillover, cobwebs, and dirt. We use a well-known supervised attention-neural-network architecture to classify the four types of package defects effectively. In this study, we use three steps to decide the best strategies. First, we find the best location of channel attention blocks for the deep attention network. After that, we compare two image preprocessing methods to enhance the features of defect. To understand if regularize the background trend will improve the performance or not, we create two kinds of dataset, rotated and non-rotated. Our study improves traditional AOI methods. The experimental results show that the proposed procedures can extract the package defects with interlacing background efficiently." @default.
- W3122269694 created "2021-02-01" @default.
- W3122269694 creator A5033379223 @default.
- W3122269694 creator A5036001913 @default.
- W3122269694 creator A5069670059 @default.
- W3122269694 date "2020-12-01" @default.
- W3122269694 modified "2023-09-27" @default.
- W3122269694 title "Using Deep Attention Networks to Extract Defects in Crisscross Background" @default.
- W3122269694 cites W2125629257 @default.
- W3122269694 cites W2512995176 @default.
- W3122269694 cites W2555875178 @default.
- W3122269694 cites W2884585870 @default.
- W3122269694 cites W2963420686 @default.
- W3122269694 cites W2963495494 @default.
- W3122269694 doi "https://doi.org/10.1109/icpai51961.2020.00053" @default.
- W3122269694 hasPublicationYear "2020" @default.
- W3122269694 type Work @default.
- W3122269694 sameAs 3122269694 @default.
- W3122269694 citedByCount "0" @default.
- W3122269694 crossrefType "proceedings-article" @default.
- W3122269694 hasAuthorship W3122269694A5033379223 @default.
- W3122269694 hasAuthorship W3122269694A5036001913 @default.
- W3122269694 hasAuthorship W3122269694A5069670059 @default.
- W3122269694 hasConcept C108583219 @default.
- W3122269694 hasConcept C153180895 @default.
- W3122269694 hasConcept C154945302 @default.
- W3122269694 hasConcept C31972630 @default.
- W3122269694 hasConcept C34736171 @default.
- W3122269694 hasConcept C41008148 @default.
- W3122269694 hasConcept C52622490 @default.
- W3122269694 hasConcept C89600930 @default.
- W3122269694 hasConceptScore W3122269694C108583219 @default.
- W3122269694 hasConceptScore W3122269694C153180895 @default.
- W3122269694 hasConceptScore W3122269694C154945302 @default.
- W3122269694 hasConceptScore W3122269694C31972630 @default.
- W3122269694 hasConceptScore W3122269694C34736171 @default.
- W3122269694 hasConceptScore W3122269694C41008148 @default.
- W3122269694 hasConceptScore W3122269694C52622490 @default.
- W3122269694 hasConceptScore W3122269694C89600930 @default.
- W3122269694 hasLocation W31222696941 @default.
- W3122269694 hasOpenAccess W3122269694 @default.
- W3122269694 hasPrimaryLocation W31222696941 @default.
- W3122269694 hasRelatedWork W11691867 @default.
- W3122269694 hasRelatedWork W14665804 @default.
- W3122269694 hasRelatedWork W1469282 @default.
- W3122269694 hasRelatedWork W2769812 @default.
- W3122269694 hasRelatedWork W4033802 @default.
- W3122269694 hasRelatedWork W4262719 @default.
- W3122269694 hasRelatedWork W6364285 @default.
- W3122269694 hasRelatedWork W6473745 @default.
- W3122269694 hasRelatedWork W7789328 @default.
- W3122269694 hasRelatedWork W5443255 @default.
- W3122269694 isParatext "false" @default.
- W3122269694 isRetracted "false" @default.
- W3122269694 magId "3122269694" @default.
- W3122269694 workType "article" @default.