The robustness of some scale-spaces.
British Machine Vision ConferencePublished 1 January 1997
Richard Harvey, Alison Bosson, Jenny Bangham
Citations21
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is found that the standard diffusion-based systems are not as insensitive to noise and occlusion as one might wish.
Abstract
There are several methods for forming a scale-space and they may be classified as being based on diffusion or morphology. However it is rare for the methods to be compared. Here we outline a method for such a comparison based on robustness and give results for linear diffusion, the most widely studied method, and a sieve (a new morphological method). We find that the standard diffusion-based systems are not as insensitive to noise and occlusion as one might wish.
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceScale-space and edge detection using anisotropic diffusion
12,040 Citations1990Pietro Perona, Jitendra Malik
Biological CyberneticsThe structure of images
2,406 Citations1984Jan J. Koenderink
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.
Elsevier eBooksSCALE-SPACE FILTERING
2,353 Citations1987Andrew Witkin
Scale-space filtering is a method that describes signals qualitatively, managing the ambiguity of scale in an organized and natural way.
Scale-Space Theory in Computer Vision
2,148 Citations1994Tony Lindeberg
Journal of Theoretical BiologyBiological shape and visual science (part I)
1,160 Citations1973H.E. Blum
IEEE Transactions on Pattern Analysis and Machine IntelligenceRadiometric CCD camera calibration and noise estimation
725 Citations1994Glenn Healey, Raghava Kondepudy
Using physical models for charged-coupled device (CCD) video cameras and material reflectance, the variation in digitized pixel values that is due to sensor noise and scene variation is quantify.
IEEE Transactions on Acoustics Speech and Signal ProcessingMorphological filters--Part I: Their set-theoretic analysis and relations to linear shift-invariant filters
662 Citations1987Petros Maragos, Ronald W. Schafer
The representation of classical linear filters in terms of morphological correlations, which involve supremum/infimum operations and additions, are introduced and demonstrate the power of mathematical morphology as a unifying approach to both linear and nonlinear signal-shaping strategies.
IEEE Transactions on Image ProcessingFlat zones filtering, connected operators, and filters by reconstruction
514 Citations1995Philippe Salembier, J. Serra
It is shown that from any connected operator acting on sets, one can construct a connected operator for functions (however, it is not the unique way of generating connected operators for functions).
IEEE Transactions on Pattern Analysis and Machine IntelligenceA multiresolution hierarchical approach to image segmentation based on intensity extrema
221 Citations1990Lawrence M. Lifshitz, Stephen M. Pizer
A computer algorithm which segments gray-scale images into regions of interest (objects) has been developed that can provide the basis for scene analysis (including shape-parameter calculation) or surface-based, shaded-graphics display.
Computational imaging and visionGaussian Scale-Space Theory
202 Citations1997Jon Sporring, Mads Nielsen +2 more
This chapter discusses applications of Scale-Space Theory in the context of non-Linear Extensions, as well as specific cases such as multi-Scale Watershed Segmentation, and local Morse Theory for Gaussian Blurred Functions.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Connected operators and pyramids</title>
186 Citations1993Jean C. Serra, Philippe Salembier
It is shown that, from any connected operator acting on sets, one can construct a connected operator for functions and one of the most important results of this study is that, if a pyramid is based on connected operators, the flat zones of the functions increase with the level of the pyramid.
Grayscale area openings and closings, their efficient implementation and applications
174 Citations1993Luc Vincent
It was proved in [13] that the area opening of parameter of an image is the supremum of the grayscale images that are smaller than and whose regional maxima are of area greater than or equal to .
Signal ProcessingGraphs and mathematical morphology
171 Citations1989Luc Vincent
Various graphs that can be defined on a given set S of objects, depending on the intensity of the desirable neighborhood relationships are presented, and the main operators of Mathematical Morphology are defined.
Journal of Electronic ImagingMorphological scale-space preserving transforms in many dimensions
95 Citations1996Jenny Bangham
The theory of an image decomposition that the authors refer to as a sieve is developed for images defined in any finite number of dimensions, which has the additional properties of manipulability, which means that it is easy to construct pattern recognition systems, and scale-calibration, which mean that it may be used for accurate measurement.
Computational imaging and visionOn the History of Gaussian Scale-Space Axiomatics
91 Citations1997Joachim Weickert, Seiji Ishikawa +1 more
A rapidly increasing number of publications, workshops and conferences which are devoted to scale-space ideas confirms the impression that the scale- space paradigm belongs to the challenging new topics in computer vision.
Journal of Visual Communication and Image RepresentationGraph morphology
87 Citations1992H.J.A.M. Heumans, P. F. M. Nacken +2 more
This paper presents a systematic theory for the construction of morphological operators on graphs and shows how the concept of the structuring graph is used to define openings and closings, and how these operators are invariant under symmetries of the graph.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAn analysis of camera noise
83 Citations1992R.A. Boie, Ingemar J. Cox
The authors develop and test a model of the inherent noises in cameras and suggest a locally stationary model of noise for adaptive signal processing of cameras based on ionization sensors.
Analytical BiochemistryData-sieving hydrophobicity plots
37 Citations1988Jenny Bangham
Data-sieving is described here as an alternative method for identifying domains within amino acid sequences that could be applied to other series data and, in multidimensions, to images in the same way as a median filter.
IEEE Transactions on Image ProcessingMultiscale recursive medians, scale-space, and transforms with applications to image processing
27 Citations1996Jenny Bangham, P.D. Ling +1 more
The R-sieve is very fast to compute and has a close relationship to 1-D alternating sequential filters with flat structuring elements, which is useful for machine vision applications.
Scale-space from nonlinear filters
8 Citations2002Jenny Bangham, P.D. Ling +1 more
Decomposition by extrema is put into the context of linear vision systems and scale-space, and M- and N-sieve algorithms used to decompose an image, the resulting granularity is appropriate for pattern recognition.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEOptimal Morphological Filters for Pattern Restoration
7 Citations1989Dan Schonfeld, John Goutsias
A theoretical analysis of morphological filters, for the "optimal" restoration of noisy binary images is presented, and an 'optimal' solution is obtained by using fundamental tools from mathematical morphology and decision theory.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEMedian and morphological scale space filtering and zero-crossings
4 Citations1994Jenny Bangham
It is shown that sieves also do not introduce new edges, are very robust, and perform at least as well as discreet Gaussian filters when applied to sampled data.