de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Zeitschriftenartikel

A psychophysically plausible model for typicality ranking of natural scenes

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84420

Schwaninger,  A
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons84284

Vogel,  J
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Schwaninger, A., Vogel, J., Hofer, F., & Schiele, B. (2006). A psychophysically plausible model for typicality ranking of natural scenes. ACM Transactions on Applied Perception, 3(4), 333-353. doi:http://doi.acm.org/10.1145/1190036.1190037.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-0013-CFB3-E
Zusammenfassung
Natural scenes constitute a very heterogeneous stimulus class. Each semantic category contains exemplars of varying typicality. It is therefore an interesting question whether humans can categorize natural scenes consistently into a relatively small number of categories such as coasts, rivers/lakes, forests, plains, and mountains. This is particularly important for applications such as image retrieval systems. Only if typicality is perceived consistently across different individuals, a general image retrieval system makes sense. In this study we use psychophysics and computational modeling to gain a deeper understanding of scene typicality. In the first psychophysical experiment we used a forced-choice categorization task in which each of 250 natural scenes had to be classified into one of the following five categories: coasts, rivers/lakes, forests, plains, and mountains. In the second experiment, the typicality of each scene had to be rated on a fifty point scale for each of the five categories. The psychop hysical results show high consistency between participants not only in the categorization of natural scenes, but also in the typicality ratings. In order to model human perception, we then employ a computational approach that uses an intermediate semantic modeling step by extracting local semantic concepts such as rock, water, sand, etc.. Based on the human typicality ratings, we learn a psychophysically plausible distance measure that leads to a high correlation between the computational and the human ranking of natural scenes. Interestingly, model comparisons without a semantic modeling step correlated much less with human performance suggesting that our model is psychophysically very plausible.