Results 1  10
of
34
Feature detection with automatic scale selection
 International Journal of Computer Vision
, 1998
"... The fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works ..."
Abstract

Cited by 713 (34 self)
 Add to MetaCart
(Show Context)
The fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a socalled scalespace representation. Traditional scalespace theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis. This article proposes a systematic methodology for dealing with this problem. A framework is proposed for generating hypotheses about interesting scale levels in image data, based on a general principle stating that local extrema over scales of different combinations of γnormalized derivatives are likely candidates to correspond to interesting structures. Specifically, it is shown how this idea can be used as a major mechanism in algorithms for automatic scale selection, which
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 187 (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.
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 53 (11 self)
 Add to MetaCart
(Show Context)
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.
Discrete derivative approximations with scalespace properties: A basis for lowlevel feature extraction
 J. Math. Imaging Vision
, 1993
"... It is developed how discrete derivative approximations can be de ned so that scalespace properties hold exactly also in the discrete domain. Starting from a set of natural requirements on the rst processing stages of a visual system, the visual front end, an axiomatic derivation is given of how amu ..."
Abstract

Cited by 37 (15 self)
 Add to MetaCart
(Show Context)
It is developed how discrete derivative approximations can be de ned so that scalespace properties hold exactly also in the discrete domain. Starting from a set of natural requirements on the rst processing stages of a visual system, the visual front end, an axiomatic derivation is given of how amultiscale representation of derivative approximations can be constructed from a discrete signal, so that it possesses an algebraic structure similar to that possessed by the derivatives of the traditional scalespace representation in the continuous domain. A family of kernels is derived which constitute discrete analogues to the continuous Gaussian derivatives. The representation has theoretical advantages to other discretizations of the scalespace theory in the sense that operators which commute before discretization commute after discretization. Some computational implications of this are that derivativeapproximations can be computed directly from smoothed data, and that this will give exactly the same result as convolution with the corresponding derivative approximation kernel. Moreover, a number of normalization conditions are automatically satis ed. The proposed methodology leads to a conceptually very simple scheme of computations for multiscale lowlevel feature extraction, consisting of four basic steps � (i) large support convolution smoothing, (ii) small support di erence computations, (iii) point operations for computing di erential geometric entities, and (iv) nearest neighbour operations for feature detection. Applications are given demonstrating how the proposed scheme can be used for edge detection and junction detection based on derivatives up to order three.
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 32 (10 self)
 Add to MetaCart
(Show Context)
When observing a dynamic world, the size of image structures may vary over time.
Junction detection with automatic selection of detection scales and localization scales
 In IEEE International Conference on Image Processing (ICIP
, 1994
"... ..."
(Show Context)
Active Detection and Classification of Junctions by Foveation with a HeadEye System Guided by the ScaleSpace Primal Sketch
, 1992
"... ..."
Segmentation and Classification of Edges Using Minimum Description Length Approximation and Complementary Junction Cues
, 1996
"... This article presents a method for segmenting and classifying edges using minimum description length (MDL) approximation with automatically generated break points. A scheme is proposed where junction candidates are first detected in a multiscale preprocessing step, which generates junction candidat ..."
Abstract

Cited by 17 (1 self)
 Add to MetaCart
(Show Context)
This article presents a method for segmenting and classifying edges using minimum description length (MDL) approximation with automatically generated break points. A scheme is proposed where junction candidates are first detected in a multiscale preprocessing step, which generates junction candidates with associated regions of interest. These junction features are matched to edges based on spatial coincidence. For each matched pair, a tentative break point is introduced at the edge point closest to the junction. Finally, these feature combinations serve as input for an MDL approximation method which tests the validity of the break point hypotheses and classifies the resulting edge segments as either &quot;straight &quot; or &quot;curved&quot;. Experiments on real world image data demonstrate the viability of the approach.
A short introduction to the Radon and Hough transforms and how they relate to each other
, 2004
"... Extraction of primitives, such as lines, edges and curves, is often a key step in an image analysis procedure. The most popular technique for curve detection is based on the Hough transform. The original formulation of the Hough transform is inherently discrete. It is therefore difficult to assess w ..."
Abstract

Cited by 14 (1 self)
 Add to MetaCart
Extraction of primitives, such as lines, edges and curves, is often a key step in an image analysis procedure. The most popular technique for curve detection is based on the Hough transform. The original formulation of the Hough transform is inherently discrete. It is therefore difficult to assess which properties are inherent to the transformbased technique and which are due to its discrete nature. As other authors have pointed out before, the Hough transform is closely related to the Radon transform, in fact equivalent, if one is not too pedantic about the original formulations of the two transforms. With this report we hope to once again stress this relationship. The Radon transform formalism has two advantages over the Hough formalism. It has a wellfounded mathematical basis and, in our opinion, is more intuitive as well.
Representing edge models via local principal component analysis
 7th European Conference on Computer Vision
, 2002
"... Abstract. Edge detection depends not only upon the assumed model of what an edge is, but also on how this model is represented. The problem of how to represent the edge model is typically neglected, despite the fact that the representation is a bottleneck for both computational cost and accuracy. We ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
(Show Context)
Abstract. Edge detection depends not only upon the assumed model of what an edge is, but also on how this model is represented. The problem of how to represent the edge model is typically neglected, despite the fact that the representation is a bottleneck for both computational cost and accuracy. We propose to represent edge models by a partition of the edge manifold corresponding to the edge model, where each local element of the partition is described by its principal components. We describe the construction of this representation and demonstrate its benefits for various edge models. 1