Bibliothek

X
feed icon rss

Ihre E-Mail wurde erfolgreich gesendet. Bitte prüfen Sie Ihren Maileingang.

Leider ist ein Fehler beim E-Mail-Versand aufgetreten. Bitte versuchen Sie es erneut.

Vorgang fortführen?

Exportieren
Filter
  • Neural networks  (2)
  • Shape classification  (1)
  • 1
    Digitale Medien
    Digitale Medien
    Explanation facility for neural networks (1992)
    Springer
    Journal of intelligent and robotic systems 5 (1992), S. 193-206 
    Details
    ISSN: 1573-0409
    Schlagwort(e): Neural networks ; explanation facilities ; Prolog ; input characterization grammar ; text generation
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik , Maschinenbau
    Notizen: Abstract This paper give a methodology, PROLOG code, as well as an example of an explanation facility EN applicable to most neural networks. It involves How?, Why? and TRACE facilities, and is based on a general explanation degree calculation in a multilayer neural network, as well as on input node characterization grammars for synthesis of explanation text.
    Materialart: Digitale Medien
    URL: http://dx.doi.org/10.1007/BF00444296
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
    Artikel (Nationallizenzen)
    Volltext
  • 2
    Digitale Medien
    Digitale Medien
    PDL-HM: morphological and syntactic shape classification algorithm (1994)
    Springer
    Machine vision and applications 7 (1994), S. 59-68 
    Details
    ISSN: 1432-1769
    Schlagwort(e): Industrial machine vision ; Real-time processing ; Image morphology ; Hit- and-miss transform ; Picture description language ; Neural networks ; Shape classification ; Fish processing
    Quelle: Springer Online Journal Archives 1860-2000
    Thema: Informatik
    Notizen: Abstract This paper describes a novel shape classification technique in computer vision called PDL-HM, which combines the selection of morphological structuring elements from contour description languages, the extraction of shape characteristics by the hit- and-miss transform, and shape classification by a neural network. This real-time method is orientation independent and tolerates limited object overlap. It is illustrated by an application to fish species classification in an industrial enviromnent and performs excellently
    Materialart: Digitale Medien
    URL: http://dx.doi.org/10.1007/BF01215802
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
    Artikel (Nationallizenzen)
    Volltext
Schließen ⊗
Diese Webseite nutzt Cookies und das Analyse-Tool Matomo. Weitere Informationen finden Sie hier...