Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  A computational recognition system grounded in perceptual research

Wallraven, C. (2007). A computational recognition system grounded in perceptual research. PhD Thesis, Eberhard-Karls Universität, Tübingen, Germany.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-0004-C8D9-6 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0004-C8DA-5
Genre: Hochschulschrift

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://publikationen.uni-tuebingen.de/xmlui/handle/10900/49012 (Verlagsversion)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Wallraven, C1, 2, Autor           
Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: In this thesis a computational framework for visual object recognition is developed, which is based on results from perceptual research. The motivation for this approach is given by the fact that despite several decades of research in the field of computer vision, there still exists no recognition system which is able to match the visual performance of humans (or other primates). The apparent ease with which visual tasks such as recognition and categorization are solved by humans is testimony of a highly optimized visual system which not only exhibits excellent robustness and generalization capabilities but is in addition highly flexible in learning and organizing new data. In developing the framework, the underlying philosophy was to model object recognition on an abstract cognitive level rather than supplying a complete neurophysiologically plausible implementation. The proposed framework is able to model results from psychophysics and, in addition, delivers excellent recognition performance in computational recognition experiments. Furthermore, the framework also interfaces well with advanced classification schemes from machine learning thus further broadening the scope of application.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2006-10-182007
 Publikationsstatus: Erschienen
 Seiten: 172
 Ort, Verlag, Ausgabe: Tübingen, Germany : Eberhard-Karls Universität
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: -
 Art des Abschluß: Doktorarbeit

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: