Statistics of Second Order Multi-modal Feature Events and Their Exploitation in Biological and Artificial Visual Systems
In this work we investigate the multi-modal statistics of natural image sequences looking at the modalities orientation, color, optic flow and contrast transition.It turns out that second order interdependencies of local line detectors can be related to the Gestalt law collinearity. Furthermore we can show that statistical interdependencies increase significantly when we look not at orientation only but also at other modalities.
The occurrence of illusionary contour processing (in which the Gestalt law ‘collinearity’ is tightly involved) at a late stage during the development of the human visual system (see, e.g., ) makes it plausible that mechanisms involved in the processing of Gestalt laws depend on visual experience about the underlying structures in visual data.This also suggests a formalization of Gestalt laws in artificial systems depending on statistical measurements.We discuss the usage of statistical interdependencies measured in this work within an artificial visual systems and show first results.
KeywordsOptic Flow Human Visual System Natural Image Image Patch Subjective Contour
Unable to display preview. Download preview PDF.
- J. Aloimonos and D. Shulman. Integration of Visual Modules—An extension of the Marr Paradigm. Academic Press, London, 1989.Google Scholar
- A.J. Bell and T. Sejnowski.Edges are the ‘independent components’ of natural Scenes. Advances in Neural Information Processing Systems, 9:831–837, 1996.Google Scholar
- H. Elder and R.M. Goldberg. Inferential reliability of contour grouping cues in natural images. Perception Supplement, 27, 1998.Google Scholar
- M. Felsberg and G. Sommer.The monogenic Signal. IEEE Transactions on Signal Processing, 41(12), 2001.Google Scholar
- M.S. Gazzaniga. The Cognitive Neuroscience. MIT Press, 1995.Google Scholar
- D.D. Hoffman, editor. Visual Intelligence: How we create what we see. W.W. Norton and Company, 1980.Google Scholar
- N. Krüger and F. Wörgötter. Different degree of genetical prestructuring in the ontogenesis of visual abilities based on deterministic and statistical regularities. Proceedings of the Workshop On Growing up Artifacts that Live SAB 2002, 2002.Google Scholar
- N. Krüger and F. Wörgötter. Multimodal estimation of collinearity and parallelism in natural image sequences to appear in Network: Computation in Neural Systems, 2002.Google Scholar
- H.-H. Nagel.On the estimation of optic flow: Relations between different approaches and some new results. Artificial Intelligence, 33:299–324, 1987.Google Scholar
- S. Posch. Perzeptives Gruppieren und Bildanalyse. Habilitationsschrift, Universität Bielefeld, Deutscher Universitäts Verlag, 1997.Google Scholar
- S. Sarkax and K.L. Boyer. Computing Perceptual Organization in Computer Vision. World Scientific, 1994.Google Scholar