Feature Detection with Automatic Scale Selection

@article{Lindeberg2004FeatureDW,
  title={Feature Detection with Automatic Scale Selection},
  author={Tony Lindeberg},
  journal={International Journal of Computer Vision},
  year={2004},
  volume={30},
  pages={79-116}
}
  • T. Lindeberg
  • Published 1 November 1998
  • Computer Science
  • International Journal of Computer Vision
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 so-called scale-space representation. Traditional scale-space theory… Expand
Supervised Scale-Invariant Segmentation (and Detection)
TLDR
An approach to the scale-selection problem in which the construction of the detector is driven by supervised learning techniques and the resulting classification method is designed so as to achieve scale-invariance and may be thought of as a supervised version of Lindeberg's classical scheme. Expand
Detecting interpretable and accurate scale-invariant keypoints
TLDR
A novel method for detecting scale invariant keypoints that competes in repeatability with the Lowe detector, but finds more stable keypoints in poorly textured areas, and shows comparable or higher accuracy than other recent detectors, which makes it useful for both object recognition and camera calibration. Expand
Scale Selection Properties of Generalized Scale-Space Interest Point Detectors
  • T. Lindeberg
  • Mathematics, Computer Science
  • Journal of Mathematical Imaging and Vision
  • 2012
TLDR
A theoretical analysis of the scale selection properties of a generalized framework for detecting interest points from scale-space features and it is shown that the scale estimates obtained from the determinant of the Hessian operator are affine covariant for an anisotropic Gaussian blob model. Expand
Scale Selection
  • T. Lindeberg
  • Computer Science
  • Computer Vision, A Reference Guide
  • 2014
The notion of scale selection refers to methods for estimating characteristic scales in image data and for automatically determining locally appropriate scales in a scale-space representation, so asExpand
Scale selection for supervised image segmentation
TLDR
The so-called max rule is proposed, which selects a scale for each pixel to have the largest confidence in the classification across the scales, and applied to artificial and real-world image segmentation tasks, which is shown to choose the right scales for different problems and lead to better segmentation results. Expand
A New Method to Improve Feature Detection Methods Based on Scale Space
Scale-space theory provides a well-founded framework for modelling image structures at multiple scales, and the output from the scale-space representation can be used as input to a large variety ofExpand
Supervised Image Segmentation with Scale Invariance
To cope with scale variations in images, scale invariance is a desired property in many computer vision tasks. Lindeberg’s scale selection method is probably the most successfully and widely usedExpand
Edge Detection and Ridge Detection with Automatic Scale Selection
  • T. Lindeberg
  • Mathematics, Computer Science
  • International Journal of Computer Vision
  • 2004
TLDR
A mechanism is presented for automatic selection of scale levels when detecting one-dimensional image features, such as edges and ridges, with characteristic property that the selected scales on a scale-space ridge instead reflect the width of the ridge. Expand
Real-Time Scale Selection in Hybrid Multi-scale Representations
TLDR
A framework for how the computation of such scale descriptors can be performed in real time on a standard computer is presented, expressed within a novel type of multi-scale representation, referred to as hybrid multi- scale representation, which aims at integrating and providing variable trade-offs between the relative advantages of pyramids and scale-space representation. Expand
Visual object class recognition using local descriptions
TLDR
This work extended the Loupias detector by a Laplacian scale selection mechanism and could obtain superior results using this extended detector in a challenging animal classification task proposed by the MUSCLE Network-of-Excellence. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 80 REFERENCES
Edge detection and ridge detection with automatic scale selection
  • T. Lindeberg
  • Mathematics, Computer Science
  • Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1996
TLDR
A mechanism is presented for automatic selection of scale levels when detecting one-dimensional features, such as edges and ridges, and a novel concept of a scale-space edge is introduced. Expand
Junction detection with automatic selection of detection scales and localization scales
  • T. Lindeberg
  • Computer Science
  • Proceedings of 1st International Conference on Image Processing
  • 1994
TLDR
This article shows how a general heuristic principle for scale selection can be applied to the problem of detecting and localizing junctions, and the resulting method is the first junction detector with automatic scale selection. Expand
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention
  • T. Lindeberg
  • Computer Science
  • International Journal of Computer Vision
  • 2005
TLDR
A multiscale representation of grey-level shape called the scale-space primal sketch is presented, which gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottom-up data-driven way. Expand
Feature Tracking with Automatic Selection of Spatial Scales
TLDR
The problems of corner detection and blob detection are treated in detail, and a combined framework for feature tracking is presented, which overcomes some of the inherent limitations of exposing fixed-scale tracking methods to image sequences in which the size variations are large. Expand
Scale selection for differential operators
TLDR
A proper representation of scale is essential to most visual tasks requiring stable descriptors of image structure, and in certain problems, such as shape-from-texture, scale variations in an image also constitute a primary cue in its own right. Expand
A scale selection principle for estimating image deformations
TLDR
The need for incorporating an explicit mechanism for scale selection in this context, in algorithms for computing descriptors such as optic flow and for performing stereo matching is advocated. Expand
Scale-Space Filtering
  • A. Witkin
  • Mathematics, Computer Science
  • IJCAI
  • 1983
TLDR
Scale-space filtering is a method that describes signals qualitatively, managing the ambiguity of scale in an organized and natural way. Expand
The structure of images
TLDR
It is shown that any image can be embedded in a one-parameter family of derived images (with resolution as the parameter) in essentially only one unique way if the constraint that no spurious detail should be generated when the resolution is diminished, is applied. Expand
Scale and the differential structure of images
TLDR
This paper shows why the operations of scaling and differentiation cannot be separated and permits us to construct in a systematic way multiscale, cartesian differential invariants, i.e. true image descriptors that exhibit manifest invariance with respect to a change of cartesian coordinates. Expand
An Extended Class of Scale-Invariant and Recursive Scale Space Filters
TLDR
The authors show that only a discrete subset of filters gives rise to an evolution which can be characterized by means of a partial differential equation. Expand
...
1
2
3
4
5
...