Results 1  10
of
20
Edge Detection and Ridge Detection with Automatic Scale Selection
 CVPR'96
, 1996
"... When extracting features from image data, the type of information that can be extracted may be strongly dependent on the scales at which the feature detectors are applied. This article presents a systematic methodology for addressing this problem. A mechanism is presented for automatic selection of ..."
Abstract

Cited by 247 (20 self)
 Add to MetaCart
When extracting features from image data, the type of information that can be extracted may be strongly dependent on the scales at which the feature detectors are applied. This article presents a systematic methodology for addressing this problem. A mechanism is presented for automatic selection of scale levels when detecting onedimensional features, such as edges and ridges. Anovel concept of a scalespace edge is introduced, defined as a connected set of points in scalespace at which: (i) the gradient magnitude assumes a local maximum in the gradient direction, and (ii) a normalized measure of the strength of the edge response is locally maximal over scales. An important property of this definition is that it allows the scale levels to vary along the edge. Two specific measures of edge strength are analysed in detail. It is shown that by expressing these in terms of γnormalized derivatives, an immediate consequence of this definition is that fine scales are selected for sharp edges (so as to reduce the shape distortions due to scalespace smoothing), whereas coarse scales are selected for diffuse edges, such that an edge model constitutes a valid abstraction of the intensity profile across the edge. With slight modifications, this idea can be used for formulating a ridge detector with automatic scale selection, having the characteristic property that the selected scales on a scalespace ridge instead reflect the width of the ridge.
Detecting Salient BlobLike Image Structures with a ScaleSpace Primal Sketch: A Method for FocusofAttention
 INT. J. COMP. VISION
, 1993
"... This article presents: (i) a multiscale representation of greylevel shape called the scalespace primal sketch, which makes explicit both features in scalespace and the relations between structures at different scales, (ii) a methodology for extracting significant bloblike image structures from ..."
Abstract

Cited by 151 (14 self)
 Add to MetaCart
This article presents: (i) a multiscale representation of greylevel shape called the scalespace primal sketch, which makes explicit both features in scalespace and the relations between structures at different scales, (ii) a methodology for extracting significant bloblike image structures from this representations, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrating how the proposed method can be used for guiding later stage visual processes. The representation gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottomup datadriven way. In other words, it generates coarse segmentation cues, and can hence be seen as preceding further processing, which can then be properly tuned. It is argued that once such information is available, many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives intuitive results.
Shapeadapted smoothing in estimation of 3D depth cues from affine distortions of local 2D brightness structure
 IN PROC. 3RD EUROPEAN CONF. ON COMPUTER VISION
, 1994
"... Rotationally symmetric operations in the image domain may give rise to shape distortions. This article describes a way of reducing this effect for a general class of methods for deriving 3D shape cues from 2D image data, which are based on the estimation of locally linearized distortion of brightn ..."
Abstract

Cited by 68 (13 self)
 Add to MetaCart
Rotationally symmetric operations in the image domain may give rise to shape distortions. This article describes a way of reducing this effect for a general class of methods for deriving 3D shape cues from 2D image data, which are based on the estimation of locally linearized distortion of brightness patterns. By extending the linear scalespace concept into an affine scalespace representation and performing affine shape adaption of the smoothing kernels, the accuracy of surface orientation estimates derived from texture and disparity cues can be improved by typically one order of magnitude. The reason for this is that the image descriptors, on which the methods are based, will be relative invariant under a ne transformations, and the error will thus be confined to the higherorder terms in the locally linearized perspective mapping.
Shapeadapted smoothing in estimation of 3D shape cues from affine distortions of local 2D brightness structure
, 2001
"... This article describes a method for reducing the shape distortions due to scalespace smoothing that arise in the computation of 3D shape cues using operators (derivatives) de ned from scalespace representation. More precisely, we are concerned with a general class of methods for deriving 3D shap ..."
Abstract

Cited by 52 (3 self)
 Add to MetaCart
This article describes a method for reducing the shape distortions due to scalespace smoothing that arise in the computation of 3D shape cues using operators (derivatives) de ned from scalespace representation. More precisely, we are concerned with a general class of methods for deriving 3D shape cues from 2D image data based on the estimation of locally linearized deformations of brightness patterns. This class
On scale selection for differential operators
 8TH SCIA
, 1993
"... Although traditional scalespace theory provides a wellfounded framework for dealing with image structures at different scales, it does not directly address the problem of how to select appropriate scales for further analysis. This paper introduces a new tool for dealing with this problem. A heur ..."
Abstract

Cited by 49 (11 self)
 Add to MetaCart
Although traditional scalespace theory provides a wellfounded framework for dealing with image structures at different scales, it does not directly address the problem of how to select appropriate scales for further analysis. This paper introduces a new tool for dealing with this problem. A heuristic principle is proposed stating that local extrema over scales of different combinations of normalized scale invariant derivatives are likely candidates to correspond to interesting structures. Support is given by theoretical considerations and experiments on real and synthetic data. The resulting methodology lends itself naturally to twostage algorithms; feature detection at coarse scales followed by feature localization at ner scales. Experiments on blob detection, junction detection and edge detection demonstrate that the proposed method gives intuitively reasonable results.
Shape from Texture from a MultiScale Perspective
 Proc. 4th Int. Conf. on Computer Vision
, 1993
"... : The problem of scale in shape from texture is addressed. The need for (at least) two scale parameters is emphasized; a local scale describing the amount of smoothing used for suppressing noise and irrelevant details when computing primitive texture descriptors from image data, and an integration s ..."
Abstract

Cited by 38 (14 self)
 Add to MetaCart
: The problem of scale in shape from texture is addressed. The need for (at least) two scale parameters is emphasized; a local scale describing the amount of smoothing used for suppressing noise and irrelevant details when computing primitive texture descriptors from image data, and an integration scale describing the size of the region in space over which the statistics of the local descriptors is accumulated. A novel mechanism for automatic scale selection is proposed, based on normalized derivatives. It is used for adaptive determination of the two scale parameters in a multiscale texture descriptor, the windowed second moment matrix, which is defined in terms of Gaussian smoothing, first order derivatives, and nonlinear pointwise combinations of these. The same scaleselection method can be used for multiscale blob detection without any tuning parameters or thresholding. The resulting texture description can be combined with various assumptions about surface texture in order to ...
Feature Tracking with Automatic Selection of Spatial Scales
 Computer Vision and Image Understanding
, 1996
"... When observing a dynamic world, the size of image structures may vary over time. ..."
Abstract

Cited by 24 (8 self)
 Add to MetaCart
When observing a dynamic world, the size of image structures may vary over time.
The Intrinsic Structure of Optic Flow Incorporating Measurement Duality
 International Journal of Computer Vision
, 1997
"... The purpose of this report 1 is to define optic flow for scalar and density images without using a priori knowledge other than its defining conservation principle, and to incorporate measurement duality, notably the scalespace paradigm. It is argued that the design of optic flow based applicati ..."
Abstract

Cited by 20 (13 self)
 Add to MetaCart
The purpose of this report 1 is to define optic flow for scalar and density images without using a priori knowledge other than its defining conservation principle, and to incorporate measurement duality, notably the scalespace paradigm. It is argued that the design of optic flow based applications may benefit from a manifest separation between factual image structure on the one hand, and goalspecific details and hypotheses about image flow formation on the other. The approach is based on a physical symmetry principle known as gauge invariance. Dataindependent models can be incorporated by means of admissible gauge conditions, each of which may single out a distinct solution, but all of which must be compatible with the evidence supported by the image data. The theory is illustrated by examples and verified by simulations, and performance is compared to several techniques reported in the literature. 1 Introduction The conventional "spacetime" representation of a movie as...
A Minimum Cost Approach for Segmenting Networks of Lines
 International Journal of Computer Vision
, 2001
"... The extraction and interpretation of networks of lines from images yields important organizational information of the network under consideration. In this paper, a oneparameter algorithm for the extraction of line networks from images is presented. The parameter indicates the extracted saliency lev ..."
Abstract

Cited by 19 (4 self)
 Add to MetaCart
The extraction and interpretation of networks of lines from images yields important organizational information of the network under consideration. In this paper, a oneparameter algorithm for the extraction of line networks from images is presented. The parameter indicates the extracted saliency level from a hierarchical graph. Input for the algorithm is the domain specific knowledge of interconnection points. Graph morphological tools are used to extract the minimum cost graph which best segments the network.
Investigation of Approaches for the Localization of Anatomical Landmarks in 3D Medical Images
, 1997
"... this paper we present an approach to localize semiautomatically landmarks characterized by extremal isocontour curvature. The semiautomatic approach implies that a rough estimate of the landmark position centered at a volumeofinterest is interactively provided by the user as an input. The algori ..."
Abstract

Cited by 16 (10 self)
 Add to MetaCart
this paper we present an approach to localize semiautomatically landmarks characterized by extremal isocontour curvature. The semiautomatic approach implies that a rough estimate of the landmark position centered at a volumeofinterest is interactively provided by the user as an input. The algorithm then refines this position [10]. Monga and Benayoun [4] presented an approach to compute locally the curvature characteristics of isosurfaces. The gradient direction is used to define locally the tangent plane of the isosurface. Then a local parametrization is defined by setting up two arbitrary orthogonal vectors within this tangent plane. Given this parametrization they show how the principal curvatures of the isosurface and the associated principal directions can be computed. Additionally, they derive an extremality criterion based on the spatial derivative of the principal curvature in direction of the corresponding principal direction. Application of this extremality criterion in maximum curvature direction yields a 1D subset of points on the isosurface which they call ridge (or crest) lines. Thirion [6] proposed an algorithm to extract automatically isocontour curvature extrema, which he denoted extremal points, from 3D images and which then serve as input for a rigid registration algorithm. His algorithm basically uses the extremality criterion of Monga and Benayoun [4] in both principal curvature directions.