Scale-Space Theory in Computer Vision -

. .

Résumé :
This book constitutes the refereed proceedings of the First International Conference on Scale-Space Theory for Computer Vision, Scale-Space '97, held in Utrecht, The Netherlands, in July 1997. The volume presents 21 revised full papers selected from a total of 41 submissions. Also included are 2 invited papers and 13 poster presentations. This book is the first comprehensive documentation of the application of Scale-Space techniques in computer vision and, in the broader context, in image processing and pattern recognition.

Sommaire:
A review of nonlinear diffusion filtering.- Scale space versus topographic map for natural images.- On generalized entropies and scale-space.- On the duality of scalar and density flows.- Invertible orientation bundles on 2D scalar images.- Generating stable structure using Scale-space analysis with non-uniform Gaussian kernels.- Generic events for the gradient squared with application to multi-scale segmentation.- Linear spatio-temporal scale-space.- On the handling of spatial and temporal scales in feature tracking.- Following feature lines across scale.- A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation.- Supervised diffusion parameter selection for filtering SPECT brain images.- Image loci are ridges in geometric spaces.- Multiscale measures in linear scale-space for characterizing cerebral functional activations in 3D PET difference images.- Scale space analysis by stabilized inverse diffusion equations.- Intrinsic scale space for images on surfaces: The geodesic curvature flow.- Multi-spectral probabilistic diffusion using bayesian classification.- From high energy physics to low level vision.- Dynamic scale-space theories.- Recursive separable schemes for nonlinear diffusion filters.- Level set methods and the stereo problem.- Reliable classification of chrysanthemum leaves through Curvature Scale Space.- Multi-scale contour segmentation.- Reconstruction of self-similar functions from scale-space.- Multi-scale detection of characteristic figure structures using principal curvatures of image gray-level profile.- A new framework for hierarchical segmentation using similarity analysis.- Robust anisotropic diffusion: Connections between robust statistics, line processing, and anisotropic diffusion.- Fast adaptive alternatives to nonlinear diffusion in image enhancement: Green's function approximators and nonlocal filters.- A scale-space approach to shape similarity.- Multi-scale active shape description.- Scale-space filters and their robustness.- Directional anisotropic diffusion applied to segmentation of vessels in 3D images.- 3D shape representation: Transforming polygons into voxels.- Extraction of a structure feature from three-dimensional objects by scale-space analysis.- Slowed anisotropic diffusion.- Thin nets extraction using a multi-scale approach.