Relaxation labelling algorithms — a review
Image and Vision ComputingPublished 1 November 1985
Josef Kittler, J. Illingworth
Citations167
SJR quartileQ1
SJR score0.79
SNIP1.33
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
The literature pertaining to relaxation labelling is surveyed and the important theoretical advances and the interesting applications for which it has proven useful are highlighted.
Abstract
An important research topic in image processing and image interpretation methodology is the development of methods to incorporate contextual information into the interpretation of objects. Over the last decade, relaxation labelling has been a useful and much studied approach to this problem. It is an attractive technique because it is highly parallel, involving the propagation of local information via iterative processing. The paper. surveys the literature pertaining to relaxation labelling and highlights the important theoretical advances and the interesting applications for which it has proven useful.
Keywords
Computer Science
IEEE Transactions on Pattern Analysis and Machine IntelligenceStochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
17,980 Citations1984Stuart Geman, Donald Geman
The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
Artificial IntelligenceDetermining optical flow
9,940 Citations1981Berthold K. P. Horn, Brian G. Schunck
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Determining Optical Flow</title>
7,496 Citations1981Berthold K. P. Horn, Brian G. Schunck
An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences and is robust in that it can handle image sequences that are quantized rather coarsely in space and time.
Artificial IntelligenceConsistency in networks of relations
2,430 Citations1977Alan K. Mackworth
The primary aim is to provide an accessible, unified framework, within which to present the algorithms including a new path consistency algorithm, to discuss their relationships and the may applications, both realized and potential of network consistency algorithms.
IEEE Transactions on Systems Man and CyberneticsScene Labeling by Relaxation Operations
1,401 Citations1976Azriel Rosenfeld, Robert A. Hummel +1 more
This paper formulates the ambiguity-reduction process in terms of iterated parallel operations (i.e., relaxation operations) performed on an array of object, identification data.
ScienceCooperative Computation of Stereo Disparity
1,380 Citations1976David Marr, Tomaso Poggio
It is shown that this algorithm successfully extracts information from random-dot stereograms, and its implications for the psychophysics and neurophysiology of the visual system are briefly discussed.
Information SciencesNetworks of constraints: Fundamental properties and applications to picture processing
1,248 Citations1974Ugo Montanari
Constraints are treated algebraically, and the solution of a system of linear equations in this algebra provides an approximation of the minimal network, and this solution is proved exact in special cases, e.g., for tree-like and series-parallel networks and for classes of relations for which a distributive property holds.
IEEE Transactions on Pattern Analysis and Machine IntelligenceOn the Foundations of Relaxation Labeling Processes
891 Citations1983Robert A. Hummel, Steven W. Zucker
It is shown that the problem of finding consistent labelings is equivalent to solving a variational inequality, and a procedure nearly identical to the relaxation operator derived under restricted circum-stances serves in the more general setting.
Understanding Line drawings of Scenes with Shadows
879 Citations1975David L. Waltz
A detailed discussion of the standard approach to computer interpretation of line drawings as three-dimensional scenes as well as some alternative approaches to this approach are discussed.
Artificial IntelligenceNumerical shape from shading and occluding boundaries
675 Citations1981Katsushi Ikeuchi, Berthold K. P. Horn
An iterative method for computing shape from shading using Occluding boundary information iteratively, using occluding boundaries information to supply boundary conditions and good initial values are found at certain points to help reduce the number of iterations required to reach a reasonable solution.
Artificial IntelligenceOn seeing things
674 Citations1971Mark Clowes
It is argued that at least two types of description of the pattern must be utilised if any significant pattern generalisation is to be achieved, and in general that all picture interpretation tasks involve descriptions in two domains.
Springer series in information sciencesMultiresolution Image Processing and Analysis
660 Citations1984Azriel Rosenfeld
A Hierarchical Image Analysis System Based Upon Oriented Zero Crossings of Bandpassed Images and a Tutorial on Quadtree Research.
Impossible Objects as Nonsense Sentences
311 Citations2012David A. Huffman
The βCDTriazole and βCDGAL ligands were found to form weaker inclusion complexes with the positively charged drug DNR at an acidic pH than in a neutral medium in which the drug dissociates to its neutral, uncharged form.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe Consistent Labeling Problem: Part I
287 Citations1979Robert M. Haralick, Linda G. Shapiro
It is shown that Latin square puzzles, finding N-ary relations, graph or auto-mata homomorphisms, graph colorings, as well as determining satisfiability of propositional logic statements and solving scene and edge labeling problems, are all special cases of the general consistent labeling problem.
IEEE Transactions on Pattern Analysis and Machine IntelligenceShape Matching Using Relaxation Techniques
265 Citations1979Larry S. Davis
This approach was tested on a data base consisting of digitized coastlines in various map projections and found that in nearly all cases, all matches except the correct one were eliminated by the relaxation processes.
Pattern RecognitionPoint pattern matching by relaxation
265 Citations1980Sanjay Ranade, Azriel Rosenfeld
This paper discusses a method of point pattern matching that can define a figure of merit for δij according to how closely other point pairs coincide underδij, and its possible advantages relative to other methods are discussed.
IEEE Transactions on ComputersAn Application of Relaxation Labeling to Line and Curve Enhancement
219 Citations1977Zucker, Hummel +1 more
A relaxation process is described and is applied to the detection of smooth lines and curves in noisy, real world images, effective even for curves of low contrast, and even when many curves lie close to one another.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA New Probabilistic Relaxation Scheme
185 Citations1980Bezalel Peleg
The results are compared with previous work on probabilistic relaxation labeling, and examples are given from the image segmentation domain, to applications of the new scheme in text processing.
IEEE Transactions on Pattern Analysis and Machine IntelligenceImproving Consistency and Reducing Ambiguity in Stochastic Labeling: An Optimization Approach
180 Citations1981Olivier Faugeras, Marc-Antoine Berthod
A projected gradient algorithm is developed to minimize the criterion and it is shown that the minimization procedure can be implemented in a highly parallel manner.
Artificial IntelligenceCooperating processes for low-level vision: A survey
155 Citations1981Larry S. Davis, Azriel Rosenfeld
Cooperating local parallel processes can be used as aids in assigning numerical or symbolic labels to image or scene parts in low-level vision.
Artificial IntelligenceConsistent-labeling problems and their algorithms: Expected-complexities and theory-based heuristics
150 Citations1983Bernard Nudel
Expected-complexity analyses for the traditional backtrack algorithm as well as for two more recent algorithms that have been found empirically to be significant improvements: forward checking and word-wise forward checking are carried out.
Computer Graphics and Image ProcessingRelaxation and constrained optimization by local processes
122 Citations1979Shimon Ullman
A general method for designing networks of locally interconnected simple processors that include the network of interconnections among the participating processors, as well as the iterative computation to be performed by each processor is described.
Computer Vision Systems
122 Citations2010Sundaram Gunasekaran
Among the many available methods for food quality evaluation, computer vision has proven to be the most powerful, especially for nondestructively extracting and quantifying many features that have direct relevance to food quality assessment and control.
Image and Vision ComputingContextual classification of multispectral pixel data
114 Citations1984Josef Kittler, J. Föglein
Contextual statistical decision rules for classification of lattice-structured data such as pixels in multispectral imagery are developed and their recursive implementation is shown to have a strong resemblance to relaxation algorithms.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRelaxation Matching Techniques-A Comparison
101 Citations1985Keith Price
A general matching procedure for comparing semantic network descriptions of images is developed, and an automatic segmentation and description system is used to produce the image representations so that the matching procedures must cope with variations in feature values, missing objects, and possible multiple matches.
Pattern RecognitionSegmentation of natural scenes
92 Citations1987Bir Bhanu, Bahram A. Parvin
A new simple and computationally efficient approach to image segmentation via recursive region splitting and merging is presented, based on a generalization of a two-class gradient relaxation method.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDecision Making in Context
86 Citations1983Robert M. Haralick
From a Bayesian decision theoretic framework, it is shown that the reason why the usual statistical approaches do not take context into account is because of the assumptions made on the joint prior probability function andBecause of the simplistic loss function chosen.
Communications of the ACMBreaking substitution ciphers using a relaxation algorithm
85 Citations1979Shmuel Peleg, Azriel Rosenfeld
In this paper the problem of breaking substitution ciphers is represented as a probabilistic labeling problem, where every code letter is assigned probabilities of representing plaintext letters, and updated in parallel for all code letters, using joint letter probabilities.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSemantic Description of Aerial Images Using Stochastic Labeling
77 Citations1981Olivier Faugeras, Keith Price
A method used to compute initial likelihoods and compatibilities is described, derived from an earlier symbolic matching procedure, but was modified to provide the data needed for application of the labeling method.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Relaxation Method for Multispectral Pixel Classification
77 Citations1980Jan‐Olof Eklundh, Hiroshi Yamamoto +1 more
In experiments using a color image of a house, the relaxation approach gave markedly superior performance; relaxation eliminated 4-8 times as many errors as the other methods did.
IEEE Transactions on Pattern Analysis and Machine IntelligenceBlob Detection by Relaxation
76 Citations1981Alan Danker, Azriel Rosenfeld
A discussion of the processes working independently and together using a pyramidal relaxation structure, the use of the closedness of contours as an additional information source, and the extension of cooperating relaxation processes to a time sequence of images are given.
Pattern Recognition LettersThe least-disturbance principle and weak constraints
64 Citations1983Andrew Blake
A strategy is proposed for this case, by construction of convex envelopes and by the use of 'graduated' non-convexity, for adjusting a set of real-valued labels to satisfy certain constraints.
Defense Technical Information Center (DTIC)MSYS: A System for Reasoning About Scenes.
63 Citations1975Jay M. Tenenbaum, Barrow,H G
MSYS is a system for reasoning with uncertain information and inexact rules of inference that contributes to the interpretation of visual features in scene analysis by repeatedly applying rules until a consistent set of likelihood values is attained.
Pattern RecognitionSome experiments in relaxation image matching using corner features
62 Citations1983Cheng-ye Wang, Hanfang Sun +2 more
A relaxation method based on patterns of local features is used to find matches between pairs of images or subimages that differ in position or orientation, yielding good results for TV images of objects such as tools and industrial parts, as well as for aerial images of terrain.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe Consistent Labeling Problem: Part II
61 Citations1980Robert M. Haralick, Linda G. Shapiro
It is shown that Latin square puzzles, finding N-ary relations, graph or auto-mata homomorphisms, graph colorings, as well as determining satisfiability of propositional logic statements and solving scene and edge labeling problems, are all special cases of the general consistent labeling problem.
Springer series in information sciencesMultilevel Relaxation in Low-Level Computer Vision
59 Citations1984Frank Glazer
Variational (cost minimization) and local constraint approaches are generally applicable to problems in low-level vision and are applied to the problem of computing optic flow from dynamic images.
Iterative Histogram Modification, 2
51 Citations1977Shmuel Peleg
Histogram peaks can be sharpened using an iterative process in which large bins grow at the expense of nearby smaller bins to facilitate compressing or segmenting it.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRelaxation: Evaluation and Applications
48 Citations1981György Fekete, Jan‐Olof Eklundh +1 more
Probabilistic relaxation labeling processes are iterative parallel schemes that use contextual information to reduce local ambiguities.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSegmentation of Images Having Unimodal Distributions
48 Citations1982Bir Bhanu, Olivier Faugeras
IEEE Transactions on Pattern Analysis and Machine IntelligenceContinuous Relaxation and Local Maxima Selection: Conditions for Equivalence
47 Citations1981Steven W. Zucker, Yvan G. Leclerc +1 more
A new perspective toward relaxation is introduced-that of considering it as a process for reordering labels attached to nodes in a graph, to establish the formal equivalence between relaxation and another widely used algorithm, local maxima selection.
Discrete Relaxation for Matching Relational Structures
46 Citations1978Les Kitchen
Local constraint analysis ('discrete relaxation') is used to reduce ambiguity in matching pairs of relational structures if the set of possible local properties is sufficiently large, this generally results in unambiguous identifications after only a few iterations.
IEEE Transactions on Pattern Analysis and Machine IntelligencePixel Labeling by Supervised Probabilistic Relaxation
45 Citations1981John A. Richards, D. A. Landgrebe +1 more
A simple modification to existing probabilistic relaxation procedures is suggested which allows the information contained in initial labels to exert an influence on the direction of relaxation throughout the process.
Relaxation Applied to Matching Quantitative Relational Structures
44 Citations1978Les Kitchen
The method is empirically shown to be very sensitive to the exact form of the updating rule used, but with the proper updating rule, the method works well, and is remarkably tolerant of measurement errors.
Computer Graphics and Image ProcessingToward a low-level description of dot clusters: Labeling edge, interior, and noise points
41 Citations1979Steven W. Zucker, Robert A. Hummel
This paper presents the first stage of an approach to computing the shapes of dot clusters, founded on the general principle that the concept of shape is derived from interactions with the visual world.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Gradient Projection Algorithm for Relaxation Methods
39 Citations1983John Mohammed, Robert A. Hummel +1 more
This work presents an extremely simple algorithm for performing the gradient projection and an independent verification of its correctness and yields a very simple finite algorithm for this problem.
IEEE Transactions on Systems Man and CyberneticsOn the Accuracy of Pixel Relaxation Labeling
39 Citations1981Prachi Swain, John A. Richards +1 more
Image and Vision ComputingAn optimization approach to relaxation labelling algorithms
36 Citations1983S.A. Lloyd
Two new algorithms which minimize this cost function more efficiently are introduced and some general comments on relaxation are presented.
Computer Graphics and Image ProcessingAn iterative gradient edge detection algorithm
36 Citations1976Robert B Eberlein
Computer Vision Graphics and Image ProcessingAn interpretation for probabilistic relaxation
34 Citations1983Robert M. Haralick
Some general conditional independence conditions are stated which give probabilistic relaxation the interpretation that each iteration computes the conditional probability of each local label given a new context which is the context of the previous iteration enlarged by one neighborhood width.
IEEE Transactions on Systems Man and CyberneticsArrangements, Homomorphisms, and Discrete Relaxation
33 Citations1978Robert M. Haralick, Jesse S. Kartus
It is shown how homomorphisms between arrangements, which are labeled N-ary relations, are the natural solutions to some problems requiring the integration of low-level and high-level information.
IEEE Transactions on Pattern Analysis and Machine IntelligenceStudies in Global and Local Histogram-Guided Relaxation Algorithms
31 Citations1982Paul Nagin, Allen R. Hanson +1 more
An image segmentation algorithm based on histogram clustering and probabilistic relaxation labeling is explored and a potential solution is shown to be obtainable by using orientation dependent compatibility coefficients and localizing the scope of the algorithm to small subimages followed by a merging of the segmented subimages.
Computer Graphics and Image ProcessingA method of deriving compatibility coefficients for relaxation operators
29 Citations1979Hiromichi Yamamoto
A simpler method from a viewpoint of both simplicity and accuracy is derived, based on information-theoretic concepts, and the effectiveness of this method is demonstrated in a set of numerical experiments.
Computer Vision Graphics and Image ProcessingOn compatibility and support functions in probabilistic relaxation
28 Citations1986Josef Kittler, J. Föglein
It is discussed how the choice of heuristic compatibility and support functions should depend on the type of contextual information to be exploited (spatial relationship between objects, correlation of observations).
Computer Graphics and Image ProcessingCompatibilities and the fixed points of arithmetic relaxation processes
23 Citations1980Robert M. Haralick, John Mohammed +1 more
Computer Graphics and Image ProcessingRecognition of occluded shapes using relaxation
22 Citations1982Wallace S. Rutkowski
Relaxation methods used to segment and recognize shapes that have ambiguous segmentations and that are in contact with other shapes are extended to handle major occlusions or missing parts using a general method of representing shapes by primitive boundary segments.
The Computer JournalComputer Architecture for Solving Consistent Labelling Problems
21 Citations1985J. Ullmann
The paper discusses and illustrates solutions consisting of special hardware to accomplish the required constraint propagation and an asynchronous network of intercommunicating computers to accomplished the tree search in parallel.
Computer Graphics and Image ProcessingA product rule relaxation method
21 Citations1980Robert Kirby
The experiments showed that in some applications, the product rule converges more rapidly to estimates that permit making reasonable decisions than did a previous formula using arithmetic averaging.
Computer Graphics and Image ProcessingSome properties of stochastic labeling procedures
19 Citations1982Tommy Elfving, Jan‐Olof Eklundh
Computer Graphics and Image ProcessingAmbiguity reduction in handwriting with ambiguous segmentation and uncertain interpretation
18 Citations1979Bezalel Peleg
An iterative relaxation algorithm is presented that considerably reduces the number of possible interpretations for the handwriting, while preserving the most likely interpretations.
IEEE Transactions on ComputersCurve Segmentation by Relaxation Labeling
18 Citations1977Davis, Rosenfeld
This correspondence discusses parallel iterative methods of segmenting the border of a shape into "angles" and "sides," and examples are given of their effects on various types of shapes.
Pattern RecognitionStructural pattern recognition, homomorphisms, and arrangements
17 Citations1978Robert M. Haralick
The methodology suggested in the paper provides a structural pattern recognition generalization to phrase-structured syntactic pattern recognition.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAdaptive Relaxation Labeling
14 Citations1984H. M. Kalayeh, D. A. Landgrebe
It is shown that by having nonstationary compatibility coefficients (NSCC's) the PRL stabilizes about the minimum error which is obtained during the early iterations.
Computer Vision Graphics and Image ProcessingA note on discrete relaxation
14 Citations1984Thomas C. Henderson
The earliest applications of symbolic relaxation methods involved a “discrete” relaxation which is shown to be restriction of the general relaxation process to systems of Boolean inequalities which take values over the two element set {0, 1}.
IEEE Transactions on Systems Man and CyberneticsAnalysis of relaxation processes: The two-node two-label case
13 Citations1983Dianne P. O’Leary, Bezalel Peleg
It is shown that the choice of coefficients is very important for relaxation processes, and the proper selection of coefficients will be much more important in the general case involving larger numbers of nodes and labels.
Solving the General Consistent Labeling (or Constraint Satisfaction) Problem: Two Algorithms and their Expected Complexities
12 Citations1983Bernard Nudel
This paper presents two algorithms for solving the general Consistent Labeling Problem and for each of these the expected complexity is given under a simple statistical model for the distribution of problems.
IEEE Transactions on Systems Man and CyberneticsA Use of Continuity in Character Recognition
11 Citations1974J. R. Ullmann
This paper introduces a new and highly parallel method of exploiting continuity and is shown experimentally to yield lower error rates than a comparable method of recognition that does not take account of continuity.
Computer Vision Graphics and Image ProcessingAn experiment in multispectral, multitemporal crop classification using relaxation techniques
10 Citations1983Larry S. Davis, Chengye Wang +1 more
The paper describes the result of an experimental study concerning the use of probabilistic relaxation for improving pixel classification rates and two LACIE sites were used in the study.
Computer Graphics and Image ProcessingDecomposition and decentralization techniques in relaxation labeling
10 Citations1981Olivier Faugeras
This paper proposes two classes of algorithms that reduce the difficulty of assigning names to objects in a scene by replacing a “global” problem of large dimensionality with a series “local” problems of smaller dimensionality while insuring that the solutioos of the ‘local’ problems are the same as those of the”global’ ones.
Internet Archive (Internet Archive)A Design Method for Relaxation Labeling Applications
9 Citations2015Robert A. Hummel
This theory allows the relaxation labeling algorithm, introduced in Rosenfeld, Hummel, Zucker, 1976, to be interpreted as a method for finding consistent labelings, and allows specific applications to be tailored in accordance with intended design goals.
IEEE Transactions on Information TheoryA consistency technique for pattern association
8 Citations1962J. R. Ullmann
A new technique based on the consistency of partial classifications is compared with other techniques for pattern association in the light of computer simulations and other considerations.
Computer Vision Graphics and Image ProcessingClassification by discrete optimization
8 Citations1984Bezalel Peleg
An approach to classification is described where an evaluation function is available, and the major difference between this approach and previous optimization attempts is the use of deterministic ratter than probabilistic classifications.
National Conference on Artificial IntelligenceConsistent-labeling problems and their algorithms
8 Citations1982Bernard Nudel
Two new classes of theories have been developed giving the expected complexities of three Consistent-Labeling Problem, or Constraint-Satisfaction, algorithms: Backtracking, Forward Checking and Word-wise Forward Checking, and have the potential to afford significant savings for any individual CLP, by predicting, prior to search, good orderings for use in solving that CLP.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAugmented Relaxation Labeling and Dynamic Relaxation Labeling
6 Citations1982Stephen A. Kuschel, Carl V. Page
Augmented relaxation labeling is a two stage process which contains a separate relaxation stage with a top-down direction capability for specific pixel label updating and dynamic relaxation is a one step process where every pixel label is updated through the dynamic neighborhoods.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Relaxation Matching Applied To Aerial Images</title>
6 Citations1981Keith Price
A symbolic matching system which can be used for a variety of matching tasks in scene analysis and is designed to handle many of the problems encountered in the analysis of real scenes.
Computer Graphics and Image ProcessingSome experiments on LANDSAT pixel classification using relaxation operators
6 Citations1980Hiromichi Yamamoto
Two experimental studies of estimating land use classification in LANDSAT imagery by use of iterative relaxation operators are presented and classification accuracy in various kinds of terrain areas is studied.
Pattern RecognitionStrip detection using relaxation
6 Citations1980Alan Danker, Azriel Rosenfeld
Experiments in the detection of parallel sided strips using a relaxation-like process which iteratively reinforces collinear or anti-parallel edges using two types of data, tree trunks and runways.
IEEE Transactions on Systems Man and CyberneticsThe Application of Relaxation to Waveforms with Ambiguous Segmentations
6 Citations1979F. R. D. Velasco, Azriel Rosenfeld
An extension of the discrete relaxation operator is proposed which can be applied to waveforms with ambiguous segmentations using just one relaxation network.
Pattern RecognitionMulti-resolution relaxation
5 Citations1983Karthik Narayanan, Dianne P. O’Leary +1 more
This paper investigates the possibility of using “relaxation” methods of probability adjustment and steepest-descent methods of cost function minimization at two (or more) resolutions in order to reduce their computational cost.
Computer Graphics and Image ProcessingVariations in relaxation labeling techniques
5 Citations1981Paul Nagin, Allen R. Hanson +1 more
The performance of region relaxation is shown to be affected by the form of compatibility coefficients and the configuration of local neighborhoods, and the compatibilities based upon conditional probabilities yield the only version that preserves image detail associated with spatially thin structures.
Pattern Recognition LettersRelaxation labelling — the principle of ‘least disturbance’
3 Citations1983Andrew Blake
A new approach to constrained labelling is described and applied to labelling edges in images to reach the nearest labelling that satisfies given constraints.
Computer Graphics and Image ProcessingRelaxation: Application to the matrix reconstruction problem
2 Citations1981E.V Krshnamurthy, K.A Narayana
A systematic approach to continuous graph labeling with application to computer vision
2 Citations1982Marc David. Diamond, N. Narasimhamurthi +1 more
Several cooperative solution algorithms based on the proposed formulation and results of the application of these algorithms to the problem of extracting line drawings are presented.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEA Relaxation Based Adaptive Filtering Algorithm
1 Citations1984Patrick Wambacq, A. Oosterlinck +1 more
An adaptive filtering algorithm that uses edge information, contained in the original image, to control a space varying convolution type filter.
Cooperation and Visual Information Processing
1 Citations1981Steven W. Zucker
This paper is an attempt to develop a class of parallel, synchronous mechanisms into the notion of cooperative algorithms, and to study a number of their applications, which range from practical, computer vision tasks to the modeling of human capabilities in certain visual information processing tasks.
…