On the Representation of Visual Information
Loss of information in images undergoing fine-to-coarse image transformations is analized by using an approach based on the theory of irreversible transformations. It is shown that entropy variation along scales can be used to characterize basic, low-level information and to gauge essential perceptual components of the image, such as shape and texture. The use of isotropic and anisotropic fine-to-coarse transformations of grey level images is discussed, and an extension of the approach to multi-valued images is proposed, where cross-interactions between the different colour channels are allowed.
KeywordsVisual Information Color Image Entropy Production Color Channel Isotropic Case
Unable to display preview. Download preview PDF.
- 3.S. de Groot and P. Mazur, Non-Equilibrium Thermodinamics. Amsterdam: North-Holland, 1962.Google Scholar
- 5.T. Lindeberg, Scale-space theory in computer vision. Erewhon, NC: His Publisher, 1999.Google Scholar
- 8.G. Boccignone, M. Ferraro, and T. Caelli, “Encoding visual information using anisotropic transformations, ” IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear.Google Scholar
- 9.R. Whitaker and G. Gerig, “Vector-valued di usion, ” in Geometry-Driven Diffusion in Computer Vision (B. ter Haar Romeny, ed.), (Dordrecht, The Netherlands), Kluwer Academic Publishers, 1994.Google Scholar