Scale-space Theory In Computer Vision: First International Conference, Scale-space '97, Utrecht, The Netherlands, July 2 - 4, 1997, Proceedings (lecture Notes In Computer Science)

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. 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. Bart Ter Haar Romeny ... [et Al.], Eds. Proceedings Of The First International Conference On Scale-space Theory In Computer Vision. Includes Bibliographical References And Index. A review of nonlinear diffusion filtering....Pages 1-28 Scale space versus topographic map for natural images....Pages 29-49 On generalized entropies and scale-space....Pages 51-64 On the duality of scalar and density flows....Pages 65-76 Invertible orientation bundles on 2D scalar images....Pages 77-88 Generating stable structure using Scale-space analysis with non-uniform Gaussian kernels....Pages 89-100 Generic events for the gradient squared with application to multi-scale segmentation....Pages 101-112 Linear spatio-temporal scale-space....Pages 113-127 On the handling of spatial and temporal scales in feature tracking....Pages 128-139 Following feature lines across scale....Pages 140-151 A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation....Pages 152-163 Supervised diffusion parameter selection for filtering SPECT brain images....Pages 164-175 Image loci are ridges in geometric spaces....Pages 176-187 Multiscale measures in linear scale-space for characterizing cerebral functional activations in 3D PET difference images....Pages 188-199 Scale space analysis by stabilized inverse diffusion equations....Pages 200-211 Intrinsic scale space for images on surfaces: The geodesic curvature flow....Pages 212-223 Multi-spectral probabilistic diffusion using bayesian classification....Pages 224-235 From high energy physics to low level vision....Pages 236-247 Dynamic scale-space theories....Pages 248-259 Recursive separable schemes for nonlinear diffusion filters....Pages 260-271 Level set methods and the stereo problem....Pages 272-283 Reliable classification of chrysanthemum leaves through Curvature Scale Space....Pages 284-295 Multi-scale contour segmentation....Pages 296-307 Reconstruction of self-similar functions from scale-space....Pages 309-314 Multi-scale detection of characteristic figure structures using principal curvatures of image gray-level profile....Pages 315-318 A new framework for hierarchical segmentation using similarity analysis....Pages 319-322 Robust anisotropic diffusion: Connections between robust statistics, line processing, and anisotropic diffusion....Pages 323-326 Fast adaptive alternatives to nonlinear diffusion in image enhancement: Green's function approximators and nonlocal filters....Pages 327-332 A scale-space approach to shape similarity....Pages 333-336 Multi-scale active shape description....Pages 337-340 Scale-space filters and their robustness....Pages 341-344 Directional anisotropic diffusion applied to segmentation of vessels in 3D images....Pages 345-348 3D shape representation: Transforming polygons into voxels....Pages 349-352 Extraction of a structure feature from three-dimensional objects by scale-space analysis....Pages 353-356 Slowed anisotropic diffusion....Pages 357-360 Thin nets extraction using a multi-scale approach....Pages 361-364