Abstract
We present a method for analysing frequency and orientation based on space-variant filtering (SVF). SVF response impulse depends on its spatial position. This filtering, inspired by retino-cortical map and orientation column of striate cortex, is based on a periodical projection. This special case of filtering requires less time to be computed than filter banks used for example in texture analysis. After the description of the method, the choice of the parameters which optimize the frequency cover are explained. Finally, an application for texture segmentation is presented. Results show that the high filtering selectivity makes the texture segmentation possible, even if these textures have close spectra.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Ahalt A., Krishnamurthy A.K., Chen P. and Melton D.E.: Competitive learning algorithms for quantization. Neural Networks, 3 (1990) 277–290.
Bauer R. and Dow B.M.: Local and global principles of striate cortical organization: an advanced model. Biological Cybernetics, 64 (1991) 477–483.
Bovik A.C. and al.: Multichannel texture analysis using localised spatial filters. IEEE PAMI, 48 (1) (1990) 55–73.
Brodatz P.: Textures: A photographic Album for artists and designers. Dover Publications Inc, (1966).
De Valois R. and al.: The orientation and direction selectivity of cells in macaque visual cortex. Vision Res., 22 (1982) 545–559.
Jain A.K. and Farrokhnia: Unsupervised texture segmentation using gabor filters. Pattern Recognition, 24 (12) (1991) 1167–1186.
Mallot H.A., Von Seelen W. and Giannakopoulos F.: Neural Mapping and Space-Variant Image Processing. Neural Networks, 3 (1990) 245–263.
Palagi P.M. et Guérin-Dugué: An architecture for texture segmentation: from Energy Feature to Region Detection. IWANN, (1995) 956–962.
Worgotter F., Niebur E.: Cortical column design: a link between the maps of preferred orientation and orientation tuning strength? Biological Cybernetics, 70 (1993) 1–13.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Croll, C., Pellerin, D., Hérault, J. (1997). Multidimensional filtering inspired by retino-cortical projection: Application to texture segmentation. In: Mira, J., Moreno-DÃaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032568
Download citation
DOI: https://doi.org/10.1007/BFb0032568
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive