Generic neighborhood operators
IEEE Transactions on Pattern Analysis and Machine IntelligencePublished 1 June 1992
Jan J. Koenderink, Andrea J. van Doorn
Citations234
SJR quartileQ1
SJR score3.91
SNIP5.99
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
A method that treats linear neighborhood operators within a unified framework that enables linear combinations, concatenations, resolution changes, or rotations of operators to be treated in a canonical manner is presented.
Abstract
A method that treats linear neighborhood operators within a unified framework that enables linear combinations, concatenations, resolution changes, or rotations of operators to be treated in a canonical manner is presented. Various families of operators with special kinds of symmetries (such as translation, rotation, magnification) are explicitly constructed in 1-D, 2-D, and 3-D. A concept of 'order' is defined, and finite orthonormal bases of functions closely connected with the operators of various orders are constructed. Linear transformations between the various representations are considered. The method is based on two fundamental assumptions: a decrease of resolution should not introduce spurious detail, and the local operators should be self-similar under changes of resolution. These assumptions merely sum up the even more general need for homogeneity isotropy, scale invariance, and separability of independent dimensions of front-end processing in the absence of a priori information.>
Keywords
Computer Science
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.
Journal of NeurophysiologyAn evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex
1,687 Citations1987J.P. Jones, L. A. Palmer
It seems that an optimal strategy has evolved for sampling images simultaneously in the 2D spatial and spatial frequency domains and the Gabor function provides a useful and reasonably accurate description of most spatial aspects of simple receptive fields.
DSpace@MIT (Massachusetts Institute of Technology)Finding Edges and Lines in Images
807 Citations1983John Canny
This thesis is an attempt to formulate a set of edge detection criteria that capture as directly as possible the desirable properties of an edge operator.
IEEE Transactions on Pattern Analysis and Machine IntelligenceUniqueness of the Gaussian Kernel for Scale-Space Filtering
798 Citations1986Jean Babaud, Andrew Witkin +2 more
It is shown that the Gaussian probability density function is the only kernel in a broad class for which first-order maxima and minima, respectively, increase and decrease when the bandwidth of the filter is increased.
Biological CyberneticsRepresentation of local geometry in the visual system
712 Citations1987Jan J. Koenderink, Andrea J. van Doorn
It is shown that a convolution with certain reasonable receptive field (RF) profiles yields the exact partial derivatives of the retinal illuminance blurred to a specified degree and how this representation can function as the substrate for “point processors” computing geometrical features such as edge curvature.
Journal of NeurophysiologyThe two-dimensional spatial structure of simple receptive fields in cat striate cortex
680 Citations1987J.P. Jones, L. A. Palmer
A reverse correlation method is developed that allows quantitative determination of visual receptive-field structure in two spatial dimensions and it is demonstrated that thereverse correlation method yields results with several desirable properties, including convergence and reproducibility independent of modest changes in stimulus parameters.
Pattern Recognition LettersA spatial filtering approach to texture analysis
221 Citations1985James M. Coggins, Anil K. Jain
A statistic for determining the number of different textures in the image is developed and demonstrated and a theory regarding the information processing strategies in human vision motivates the development of a texture feature space.
Journal of the Optical Society of America AEfficiency of a model human image code
209 Citations1987Andrew B. Watson
A code modeled on the simple cells of the primate striate cortex is explored, which maps a digital image into a set of subimages (layers) that are bandpass in spatial frequency and orientation and which is reconstructed from the code.
Journal of the Optical Society of America ATwo-dimensional curvature operators
137 Citations1988Jan J. Koenderink, Whitman Richards
This work analyzes how curvature can be computed by using two-dimensional operators and shows the relation of this approach to the one-dimensional methods currently in use.
Computer Vision Graphics and Image ProcessingDeblurring Gaussian blur
130 Citations1987Robert A. Hummel, Benjamin B. Kimia +1 more
Biological CyberneticsVisual detection of spatial contrast; Influence of location in the visual field, target extent and illuminance level
120 Citations1978Jan J. Koenderink, Andrea J. van Doorn
A model is proposed that permits the prediction of contrast detection thresholds for arbitrary spatial patterns and an explanation is offered for certain invariance properties of spatial contrast detection that seems to possess promising generality.
Journal of the Optical Society of America AFingerprints theorems for zero crossings
97 Citations1985Alan Yuille, Tomaso Poggio
Biological CyberneticsOperational significance of receptive field assemblies
80 Citations1988Jan J. Koenderink
This theory not only permits one to describe the existing structure in a particularly attractive, modular way, but also enables one to predict the type of connections necessary for the embodiment of specific visual capabilities, and to find the neural assemblies involved in specific visual tasks.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA hitherto unnoticed singularity of scale-space
39 Citations1989Jan J. Koenderink
The structure of scale space in an infinitesimal neighborhood of such a singularity is explored and the effect of the singularity of mappings between copies of an image at different levels of resolution is evaluated and checked with a numerical calculation.
PubMedReceptive fields and the representation of visual information.
38 Citations1986Zucker Sw, Hummel Ra
An explicit formula for constructing large receptive fields from small ones is derived, and the notion of de-blurring to derive interpolation filters for hyperacuity is introduced.
Biological CyberneticsA self-similar stack model for human and machine vision
35 Citations1986G. J. Burton, Nigel D. Haig +1 more
A new model is proposed that not only exhibits the major properties of primate spatial vision but also has a structure that can be implemented efficiently in a machine vision system.
Vision ResearchVisibility of blobs with a gaussian luminance profile
34 Citations1989P. Bijl, Jan J. Koenderink +1 more
The measurements show that the visual system has a very large bandwidth and that the presence of edges or luminance transitions in the visual field can diminish the sensitivity to a stimulus considerably, even when they are rather distant.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEMultiscale Vector Fields for Image Pattern Recognition
7 Citations1990Kah-Chan Low, James M. Coggins