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 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.