Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention

  title={Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention},
  author={Tony Lindeberg},
  journal={International Journal of Computer Vision},
  • T. Lindeberg
  • Published 1 December 1993
  • Computer Science
  • International Journal of Computer Vision
This article presents: (i) a multiscale representation of grey-level shape called the scale-space primal sketch, which makes explicit both features in scale-space and the relations between structures at different scales, (ii) a methodology for extracting significant blob-like image structures from this representation, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrating how the proposed method can be used for guiding later-stage visual… 

Perceptual Scale-Space and Its Applications

A perceptual scale-space theory which differs from the traditional image scale- space theory in two aspects, and it is shown that the sketch pyramid is a more parsimonious representation than a multi-resolution Gaussian/Wavelet pyramid.

The Image Torque Operator for Contour Processing

A new tool for edge processing implementing the Gestaltism idea of edge grouping, called the Torque operator, that is designed to help detect closed contours in images, is introduced.

Real-Time Scale Selection in Hybrid Multi-scale Representations

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.

New model of region extraction based on salient region detection and scale-space primal sketch

A new model of region extraction based on salient region detection and scale-space primal sketch is developed which could lead to better results which can be used for guiding later stage processing.

Perceptual Scale Space and its Applications

Two example applications of this perceptual scale space are shown: motion tracking of objects over scales, and adaptive image displays which can efficiently show a large high resolution image in a small screen through a selective tour of its image pyramid.

Direct computation of shape cues using scale-adapted spatial derivative operators

This paper addresses the problem of computing cues to the three-dimensional structure of surfaces in the world directly from the local structure of the brightness pattern of either a single monocular image or a binocular image pair using a multi-scale descriptor of image structure called the windowed second moment matrix.

Feature Detection with Automatic Scale Selection

  • T. Lindeberg
  • Computer Science
    International Journal of Computer Vision
  • 2004
It is shown how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation and how it can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure.

Data{Driven Shifts of Attention in Wavelet Scale Space

This work proposes that image structures (objects and their features) should be represented with a minimum amount of information and uses the wavelet representation of the scale which is approximately one octave below the scale at which an object becomes smoothed out and thus indistinguishable from other objects of the same size.

Scale Saliency: a novel approach to salient feature and scale selection

This paper presents an overview of the Scale Saliency algorithm, a novel method for measuring the saliency of image regions and selecting optimal scales for their analysis, and presents a generalised version of the original algorithm which is invariant to affine transformations.

Object Categorization: The Evolution of Object Categorization and the Challenge of Image Abstraction

The results left many unsatisfied, as the images and objects were often contrived, and the resulting systems were unable to deal with real objects imaged under real conditions, but some very important principles emerged in the 1970’s, many of which are being rediscovered by today's categorization community.



Scale-space primal sketch: construction and experiments

Early processing of visual information.

  • D. Marr
  • Computer Science
    Philosophical transactions of the Royal Society of London. Series B, Biological sciences
  • 1976
It is argued that "non-attentive" vision is in practice implemented by these grouping operations and first order discriminations acting on the primal sketch, and implies that such knowledge should influence the control of, rather than interfering with, the actual data-processing that is taking place lower down.

A Multiresolution Hierarchical Approach to Image Segmentation Based on Intensity Extrema

A computer algorithm which segments gray-scale images into regions of interest (objects) has been developed. These regions can provide the basis for scene analysis (including shape-parameter

Edge Focusing

  • F. Bergholm
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1987
It is shown that ``edge focusing'', i.e., a coarse-to-fine tracking in a continuous manner, combines high positional accuracy with good noise-reduction, which is of vital interest in several applications.

Toward a Symbolic Representation of Intensity Changes in Images

  • A. Korn
  • Physics
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1988
The symbolic representation of gray-value variations is studied, with emphasis on the gradient of the image function, and a procedure is proposed to select automatically a suitable scale, and with that, the size of the right convolution kernel.

Scale and the differential structure of images

The structure of images

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.

Discrete Scale-Space Theory and the Scale-Space Primal Sketch

This thesis proposes that the canonical way to construct a scale-space for discrete signals is by convolution with a kernel called the discrete analogue of the Gaussian kernel, or equivalently by solving a semi-discretized version of the diffusion equation.

Shape from texture from a multi-scale perspective

The problem of scale in shape from texture is addressed and the proposed computational model is expressed completely in terms of different invariants defined from Gaussian derivatives at multiple scales in scale-space, allowing for various assumptions about surface texture to estimate local surface orientation.

Symbolic Construction of a 2-D Scale-Space Image

  • E. Saund
  • Mathematics
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1990
A symbolic approach to constructing a multiscale primitive shape description to 2-D binary (silhouette) shape images is presented, and two types of grouping operations are identified that aggregate edge primitives at one scale into edgePrimitives at a coarser scale and group edge Primitives into partial-region assertions.