Classification of images: ICA filters vs human perception

In this paper we compare a machine based semantic organisation of natural images with the one provided by human perception. On one hand, we have conducted a psychophysical experiment to determine a human perception space in which we have identified semantic categories. These categories and the dista...

Full description

Saved in:
Bibliographic Details
Published inSeventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings Vol. 2; pp. 251 - 254 vol.2
Main Authors Le Borgne, H., Guyader, N., Guerin-Dugue, A., Herault, J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2003
Subjects
Data mining
Filters
Humans
Image analysis
Image databases
Independent component analysis
Layout
Multidimensional systems
Multimedia databases
Psychology
Online AccessGet full text

Cover

More Information
Summary:In this paper we compare a machine based semantic organisation of natural images with the one provided by human perception. On one hand, we have conducted a psychophysical experiment to determine a human perception space in which we have identified semantic categories. These categories and the distances between images are emphasised by analysing the human response similarities with a multidimensional scaling technique called curvilinear component analysis (CCA). On the other hand, we try to perform the same scene categorisation with a computational model based on an ICA filter description.
ISBN:0780379462
9780780379466
DOI:10.1109/ISSPA.2003.1224861