Results 1  10
of
11
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.
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.
Effective scale: A natural unit for measuring scalespace lifetime
 IEEE TRANS
, 1993
"... We develop how a notion of effective scale can be introduced in a formal way. For continuous signals a scaling argument directly gives that a natural unit for measuring scalespace lifetime is in terms of the logarithm of the ordinary scale parameter. That approach is, however, not appropriate for d ..."
Abstract

Cited by 24 (5 self)
 Add to MetaCart
We develop how a notion of effective scale can be introduced in a formal way. For continuous signals a scaling argument directly gives that a natural unit for measuring scalespace lifetime is in terms of the logarithm of the ordinary scale parameter. That approach is, however, not appropriate for discrete signals, since then an in nite lifetime would be assigned to structures existing in the original signal. Here we show how such an e ective scale parameter can be de ned as to give consistent results for both discrete and continuous signals. The treatment is based upon the assumption that the probability that a local extremum disappears during a short scale interval should not vary with scale. As a tool for the analysis we give estimates of how the density of local extrema can be expected to vary with scale in the scalespace representation of different random noise signals, both in the continuous and discrete cases.
Complex Wavelet Bases, Steerability, and the MarrLike Pyramid
, 2008
"... Our aim in this paper is to tighten the link between wavelets, some classical imageprocessing operators, and David Marr’s theory of early vision. The cornerstone of our approach is a new complex wavelet basis that behaves like a smoothed version of the GradientLaplace operator. Starting from firs ..."
Abstract

Cited by 12 (6 self)
 Add to MetaCart
Our aim in this paper is to tighten the link between wavelets, some classical imageprocessing operators, and David Marr’s theory of early vision. The cornerstone of our approach is a new complex wavelet basis that behaves like a smoothed version of the GradientLaplace operator. Starting from first principles, we show that a singlegenerator wavelet can be defined analytically and that it yields a semiorthogonal complex basis of, irrespective of the dilation matrix used. We also provide an efficient FFTbased filterbank implementation. We then propose a slightly redundant version of the transform that is nearly translationinvariant and that is optimized for better steerability (Gaussianlike smoothing kernel). We call it the Marrlike wavelet pyramid because it essentially replicates the processing steps in Marr’s theory of early vision. We use it to derive a primal wavelet sketch which is a compact description of the image by a multiscale, subsampled edge map. Finally, we provide an efficient iterative
TREND: A System for Generating Intelligent Descriptions of TimeSeries Data
 In Proceedings of the IEEE International Conference on Intelligent Processing Systems (ICIPS1998
, 1998
"... A system is described that integrates knowledgebased signal processing and natural language processing to automatically generate descriptions of timeseries data. These descriptions are based on short and longterm trends in the data which are detected using wavelet analysis. The basic architecture ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
A system is described that integrates knowledgebased signal processing and natural language processing to automatically generate descriptions of timeseries data. These descriptions are based on short and longterm trends in the data which are detected using wavelet analysis. The basic architecture of the system is presented and some experimental results are shown for weather data. I. Introduction A. Motivation Every day more and more timeseries data is recorded and stored online: for example, stock prices, meteorological data, astronomical measurements and network performance statistics. The granularity of this data  the time between successive measurements  is becoming finer and finer; for example, stock prices are now recorded as often as once a minute. But how do people absorb all this information ? An effective way to digest numerical data is to view it graphically. However, this may not always be possible; the data may only be accessible by phone or the application may be...
Scalespace behaviour and invariance properties of di erential singularities. In: This volume
, 1993
"... Abstract. This article describes how a certain way of expressing lowlevel feature detectors, in terms of singularities of di erential expressions de ned at multiple scales in scalespace, simpli es the analysis of the e ect of smoothing. It is shown how such features can be related across scales, a ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
Abstract. This article describes how a certain way of expressing lowlevel feature detectors, in terms of singularities of di erential expressions de ned at multiple scales in scalespace, simpli es the analysis of the e ect of smoothing. It is shown how such features can be related across scales, and generally valid expressions for drift velocities are derived with examples concerning edges, junctions, Laplacean zerocrossings, and blobs. A number of invariance properties are pointed out, and a particular representation de ned from such singularities, the scalespace primal sketch, is treated in more detail.
Direct computation of shape cues by multiscale retinotopic processing
 J. OF COMPUTER VISION
, 1994
"... ..."
Perceptual ScaleSpace and Its Applications
 INT J COMPUT VIS
, 2008
"... When an image is viewed at varying resolutions, it is known to create discrete perceptual jumps or transitions amid the continuous intensity changes. In this paper, we study a perceptual scalespace theory which differs from the traditional image scalespace theory in two aspects. (i) In represent ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
When an image is viewed at varying resolutions, it is known to create discrete perceptual jumps or transitions amid the continuous intensity changes. In this paper, we study a perceptual scalespace theory which differs from the traditional image scalespace theory in two aspects. (i) In representation, the perceptual scalespace adopts a full generative model. From a Gaussian pyramid it computes a sketch pyramid where each layer is a primal sketch representation (Guo et al. in Comput. Vis. Image Underst. 106(1):5– 19, 2007)—an attribute graph whose elements are image primitives for the image structures. Each primal sketch graph generates the image in the Gaussian pyramid, and the changes between the primal sketch graphs in adjacent layers are represented by a set of basic and composite graph operators to account for the perceptual transitions. (ii) In computation, the sketch pyramid and graph operators are inferred, as hidden variables, from the images through Bayesian inference by stochastic algorithm, in contrast to the deterministic transforms or feature extraction, such as computing zerocrossings, extremal points, and inflection points in the image scalespace. Studying the perceptual transitions under the Bayesian framework makes it convenient to use the statistical modeling and learning tools for (a) modeling the Gestalt properties of the sketch graph, such as continuity and parallelism etc; (b) learning the most frequent graph operators,
A Galaxy of Texture Features
"... The aim of this chapter is to give experienced and new practitioners in image analysis and computer vision an overview and a quick reference to the “galaxy” of features that exist in the field of texture analysis. Clearly, given the limited space, only a corner of this vast galaxy is covered here! F ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The aim of this chapter is to give experienced and new practitioners in image analysis and computer vision an overview and a quick reference to the “galaxy” of features that exist in the field of texture analysis. Clearly, given the limited space, only a corner of this vast galaxy is covered here! Firstly, a brief taxonomy of texture analysis approaches is outlined. Then, a list of widely used texture features is presented in alphabetical order. Finally, a brief comparison of texture features and feature extraction methods based on several literature surveys is given. The aim of this chapter is to give the reader a comprehensive overview of texture features. This area is so diversive that it is impossible to cover it fully in this limited space. Thus only a list of widely used texture features is presented here. However, before that, we will first look at how these features can be used in