Matches in SemOpenAlex for { <https://semopenalex.org/work/W1985874902> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W1985874902 endingPage "1836" @default.
- W1985874902 startingPage "1827" @default.
- W1985874902 abstract "Abstract This paper proposes an artificial neural network that extracts axes of symmetry from visual patterns. The input patterns can be plane figures, complicated line drawings or gray-scaled natural images taken by CCD cameras. The network has a hierarchical multi-layered architecture, which resembles that of the lower stages of the neocognitron. It consists of a contrast-extracting layer, edge-extracting layers (simple and complex types), and layers extracting symmetry axes. The network extracts oriented edges from the input image first, and then tries to extract axes of symmetry. Our network checks conditions of symmetry, not directly from the oriented edges, but from a blurred version of them. The use of blurred signals not only reduces the computational cost greatly, but also endows the network with a large tolerance to deformation of input patterns. It is important to get blurred signals, not directly from an input image, but from the oriented edges. Although information of edge locations becomes ambiguous after the blurring operation, most of important features of the original image can still remain stable. If the input image is directly blurred, however, most of the important features in the image will be lost." @default.
- W1985874902 created "2016-06-24" @default.
- W1985874902 creator A5075935845 @default.
- W1985874902 creator A5087391146 @default.
- W1985874902 date "2006-10-01" @default.
- W1985874902 modified "2023-09-23" @default.
- W1985874902 title "Symmetry axis extraction by a neural network" @default.
- W1985874902 cites W1988809745 @default.
- W1985874902 cites W2021879571 @default.
- W1985874902 cites W2023313243 @default.
- W1985874902 cites W2068470708 @default.
- W1985874902 cites W2113625916 @default.
- W1985874902 cites W2147175193 @default.
- W1985874902 doi "https://doi.org/10.1016/j.neucom.2005.11.010" @default.
- W1985874902 hasPublicationYear "2006" @default.
- W1985874902 type Work @default.
- W1985874902 sameAs 1985874902 @default.
- W1985874902 citedByCount "17" @default.
- W1985874902 countsByYear W19858749022012 @default.
- W1985874902 countsByYear W19858749022015 @default.
- W1985874902 countsByYear W19858749022016 @default.
- W1985874902 countsByYear W19858749022017 @default.
- W1985874902 countsByYear W19858749022018 @default.
- W1985874902 countsByYear W19858749022021 @default.
- W1985874902 countsByYear W19858749022022 @default.
- W1985874902 crossrefType "journal-article" @default.
- W1985874902 hasAuthorship W1985874902A5075935845 @default.
- W1985874902 hasAuthorship W1985874902A5087391146 @default.
- W1985874902 hasConcept C153180895 @default.
- W1985874902 hasConcept C154945302 @default.
- W1985874902 hasConcept C185592680 @default.
- W1985874902 hasConcept C2524010 @default.
- W1985874902 hasConcept C2779886137 @default.
- W1985874902 hasConcept C33923547 @default.
- W1985874902 hasConcept C41008148 @default.
- W1985874902 hasConcept C43617362 @default.
- W1985874902 hasConcept C4725764 @default.
- W1985874902 hasConcept C50644808 @default.
- W1985874902 hasConceptScore W1985874902C153180895 @default.
- W1985874902 hasConceptScore W1985874902C154945302 @default.
- W1985874902 hasConceptScore W1985874902C185592680 @default.
- W1985874902 hasConceptScore W1985874902C2524010 @default.
- W1985874902 hasConceptScore W1985874902C2779886137 @default.
- W1985874902 hasConceptScore W1985874902C33923547 @default.
- W1985874902 hasConceptScore W1985874902C41008148 @default.
- W1985874902 hasConceptScore W1985874902C43617362 @default.
- W1985874902 hasConceptScore W1985874902C4725764 @default.
- W1985874902 hasConceptScore W1985874902C50644808 @default.
- W1985874902 hasIssue "16-18" @default.
- W1985874902 hasLocation W19858749021 @default.
- W1985874902 hasOpenAccess W1985874902 @default.
- W1985874902 hasPrimaryLocation W19858749021 @default.
- W1985874902 hasRelatedWork W2033914206 @default.
- W1985874902 hasRelatedWork W2042327336 @default.
- W1985874902 hasRelatedWork W2046077695 @default.
- W1985874902 hasRelatedWork W2146076056 @default.
- W1985874902 hasRelatedWork W2163831990 @default.
- W1985874902 hasRelatedWork W2378160586 @default.
- W1985874902 hasRelatedWork W2386387936 @default.
- W1985874902 hasRelatedWork W2996038082 @default.
- W1985874902 hasRelatedWork W3003836766 @default.
- W1985874902 hasRelatedWork W3047965787 @default.
- W1985874902 hasVolume "69" @default.
- W1985874902 isParatext "false" @default.
- W1985874902 isRetracted "false" @default.
- W1985874902 magId "1985874902" @default.
- W1985874902 workType "article" @default.