The “rubber-mask” technique-II. Pattern storage and recognition
Pattern RecognitionPublished 1 September 1973
Bernard Widrow
Citations69
SJR quartileQ1
SJR score2.06
SNIP2.67
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
Much of the work in pattern recognition to date is summarized, and the rubber mask technique is related to previous work, and a scheme for incorporating flexible-mask methods into a proposed pattern recognition and memory system is presented.
Abstract
This paper briefly summarizes much of the work in pattern recognition to date, and relates the rubber mask technique to previous work. A scheme for incorporating flexible-mask methods into a proposed pattern recognition and memory system is presented. A discussion based on some facts and on some conjecture of the human eye/brain system and how it recognizes patterns, possibly by flexible matching, is also presented.
Keywords
Computer Science
IEEE Transactions on Information TheoryNearest neighbor pattern classification
16,134 Citations1967Thomas M. Cover, Peter E. Hart
The nearest neighbor decision rule assigns to an unclassified sample point the classification of the nearest of a set of previously classified points, so it may be said that half the classification information in an infinite sample set is contained in the nearest neighbor.
Elsevier eBooksIntroduction to Statistical Pattern Recognition
11,121 Citations1990Keinosuke Fukunaga
A system to determine the sex of fish from their length, as accurately as possible, using a set of labelled data, together with the class label (male or female), as a training set.
ASPECTS OF THE THEORY OF SYNTAX
10,941 Citations1964Noam Chomsky
Perceptrons: an introduction to computational geometry
3,308 Citations1969Marvin Minsky, Seymour Papert
The American Journal of PsychologyFoundations of Cyclopean Perception
2,414 Citations1973Whitman Richards, Béla Julesz
The American Journal of PsychologyPrinciples of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms
1,818 Citations1963Benjamin White, Frank Rosenblatt
The background, basic sources of data, concepts, and methodology to be employed in the study of perceptrons are reviewed, and some of the notation to be used in later sections are presented.
Introduction to Statistical Pattern Recognition
1,607 Citations2011Andrew R. Webb, Keith D. Copsey
Formal Languages and Their Relation to Automata
1,341 Citations1969John E. Hopcroft, Jeffrey D. Ullman
The theory of formal languages as a coherent theory is presented and its relationship to automata theory is made explicit, including the Turing machine and certain advanced topics in language theory.
Pattern Recognition and Machine Learning
1,028 Citations1971Kebo Fu
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)ISODATA, A NOVEL METHOD OF DATA ANALYSIS AND PATTERN CLASSIFICATION
923 Citations1965Geoffrey H. Ball, David J. Hall
ISODATA, a novel method of data analysis and pattern classification, is described in verbal and pictorial terms, in terms of a two-dimensional example, and by giving the mathematical calculations that the method uses.
The American Journal of PsychologyEye and Brain: The Psychology of Seeing
832 Citations1967Jacob Beck, RL Gregory
Archives of General PsychiatryPrinciples of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms.
510 Citations1962J. Orbach
This formidable book has offered a somewhat different program involving the design and testing of brain models described as perceptrons, concerned not with devices for artificial intelligence, but, rather, with "the physical structures and neurodynamics principles which underly "natural intelligence.
The Journal of the Acoustical Society of AmericaAdaptive Antenna Systems
417 Citations1967Bernard Widrow, Patrick E. Mantey +2 more
IEEE Transactions on Information TheoryEstimation by the nearest neighbor rule
358 Citations1968Thomas M. Cover
This paper is an extension of earlier work from the problem of classification by the nearest neighbor rule to that of estimation, where the unbounded loss functions in the estimation problem introduce additional problems concerning the convergence of the unconditional risk.
Proceedings of the IEEEState of the art in pattern recognition
294 Citations1968George Nagy
This paper reviews statistical, adaptive, and heuristic techniques used in laboratory investigations of pattern recognition problems and includes correlation methods, discriminant analysis, maximum likelihood decisions minimax techniques, perceptron-like algorithms, feature extraction, preprocessing, clustering and nonsupervised learning.
IEEE Transactions on Electronic ComputersGeneration of Polynomial Discriminant Functions for Pattern Recognition
248 Citations1967Donald F. Specht
The method is based on nonparametric estimation of a probability density function for each category to be classified so that the Bayes decision rule can be used for classification and has good extrapolating ability even when the number of training patterns is quite small.
Elsevier eBooksMethodologies of Pattern Recognition
221 Citations1969
The titles include: implications of interactive graphic computers for pattern recognition methodology; statistical analysis as a tool to make patterns emerge from data; descriptive pattern analysis techniques, potentialities and problems; sequential pattern recognition systems.
IBM Journal of Research and DevelopmentOn Some Clustering Techniques
210 Citations1964Raymond Bonner
A number of methods which make use of IBM 7090 computer programs to do clustering are described, and a medical research problem is used to illustrate and compare these methods.
IEEE Transactions on Electronic ComputersComputer Interpretation of English Text and Picture Patterns
196 Citations1964Russell A. Kirsch
The paper shows how the syntactic structure of text may be described, and then goes on to suggest that a similar analysis may be performed on the class of pictures under study, to suggest as an alternative to the synthetic approach in which artificial languages are specified and then learned and used.
Human DevelopmentHow Adults and Children Search and Recognize Pictures
196 Citations2009Norman H. Mackworth, Jerome S. Bruner
The eye fixations of 20 young adults and 20 children, aged six, were recorded while they were recognizing or inspecting a series of displays.
IEEE Transactions on Information TheoryLearning without a teacher
187 Citations1966J. Spragins
This is a review paper discussing and comparing most of the approaches to learning without a teacher which have been suggested to date, and divided into six classes: guessing a sequence of hypotheses, modifications of this first approach, approximating probability densities by others more easily computed, estimating parameters of a known decision rule, theoretically exact methods which require approximations in implementation, and some miscellaneous approaches.
Communications of the ACMSyntax-directed interpretation of classes of pictures
165 Citations1966Raghavan Narasimhan
The structure of syntactic descriptive models by considering their specific application to bubble chamber pictures and how the description generated in this phase can be embedded in a larger “conversation” program is explained.
ACM Computing SurveysPicture Processing by Computer
148 Citations1969Azriel Rosenfeld
The field of picture processing by computer is reviewed from a technique-oriented standpoint and the processing of given pictures (as opposed to computer-synthesized pictures) is considered.
Proceedings of the IRELinear Decision Functions, with Application to Pattern Recognition
147 Citations1962W. H. Highleyman
This paper is concerned with the study of a particular class of categorizers, the linear decision function, which can be empirically designed without making any assumptions whatsoever about either the distribution of the receptor measurements or the a priori probabilities of occurrence of the pattern classes, providing an appropriate pattern source is available.
IEEE Transactions on Information TheoryLearning to recognize patterns without a teacher
134 Citations1967S. Fralick
This paper presents a model suitable for many problems and evolves a solution in the form of a machine that "learns" to solve the problem without external aid, said to "learn without a teacher".
Journal of the ACMParsing of Graph-Representable Pictures
119 Citations1970Alan Shaw
The bulk of the paper is concerned with the picture parsing algorithm which is an n-dimensional analog of a classical top-down string parser, and an application of an implemented system to the analysis of spark chamber film.
IEEE Transactions on Electronic ComputersLearning matrices and their applications
118 Citations1963Karl Steinbuch, U. A. W. Piske
A survey of the learning circuits which became known as learning matrices and some of their possible technological applications is given.
IEEE Transactions on Information TheoryThe use of an adaptive threshold element to design a linear optimal pattern classifier
118 Citations1966J. S. Koford, Gabriel F. Groner
It is shown that the two-category classifier derived by least-mean-square-error adaption using an equal number of sample patterns from each category is equivalent to the optimal statistical classifier if the patterns are multivariate Gaussian random variables having the same covariance matrix for both pattern categories.
Linguistic methods in picture processing
97 Citations1968W. F. Miller, Alan Shaw
By "picture processing" the authors mean the analysis and generation of pictures by computer, with or without human interaction; this definition includes both computer graphics and digital pattern recognition.
The “Rubber-Mask” Technique-I, Pattern Measurement and Analysis
89 Citations1974Bernard Widrow
Flexible templates (rubber masks) have been devised which, when fitted to natural data, can be used for measurement, data reduction, data smoothing, and classification of highly irregular waveforms and image shapes.
Pattern RecognitionThe “rubber-mask” technique—I. Pattern measurement and analysis
84 Citations1973Bernard Widrow
Specific applications to the analysis of human chromosome images, chromatographic recordings, electrocardiogram waveforms, and electroencephalogram waveforms are illustrated.
Information and ControlNonsupervised adaptive signal detection and pattern recognition
71 Citations1964David B. Cooper, Paul Cooper
It is shown in one dimension that for equiprobable component distributions of almost any functional form and differing only by translation the authors can obtain category distribution estimators which converge uniformly over the real line with probability 1.
IEEE Transactions on Biomedical EngineeringVectorcardiographic Diagnosis Using the Polynomial Discriminant Method of Pattern Recognition
60 Citations1967Donald F. Specht
This paper describes research on the application of a newly developed pattern-recognition technique called the polynomial discriminant method (PDM) to the diagnosis of heart disease as evidenced in the vectorcardiograms (an orthogonalized form of electrocardiogram).
IEEE Transactions on ComputersA Stochastic Syntax Analysis Procedure and Its Application to Pattern Classification
59 Citations1972H.C. Lee, King‐Sun Fu
Developed is a stochastic context-free language for use in pattern classification of chromosome images based on statistical decision theory with the probability of occurrence of each pattern computed from the stochastically context- free grammar.
Perception & PsychophysicsA stand camera for line-of-sight recording
56 Citations1967Norman H. Mackworth
IEEE Transactions on Automatic ControlSelf-learning--What is it?
56 Citations1968Ya. Ζ. Tsypkin
The problems of self-learning are discussed, and a general method of solving these problems is described, and the ideas of optimal algorithms which minimize the proposed performance criteria are found.
IEEE Transactions on Electronic ComputersAdaptive Systems in Pattern Recognition
32 Citations1963H. Kazmierczak, Karl Steinbuch
The perceptual superiority of the human visual system over automata is outlined comparing the properties of both systems and the existing classification methods are outlined and discussed with regard to adaptive systems.
IEEE Transactions on Electronic ComputersAn Experimental Investigation of a Mixed-Font Print Recognition System
31 Citations1966C. N. Liu, Georgia Shelton
An experimental study of a mixed-font print recognition system using 96 N-tuple recognition measurements with ternary minimum distance decision is discussed, which is capable of reading a variety of type styles at a performance level which is quite acceptable for fair to good quality print.
IBM Journal of Research and DevelopmentA Technique for Determining and Coding Subclasses in Pattern Recognition Problems
31 Citations1965R. L. Mattson, James E. Dammann
This paper describes a method for detecting and coding clusters that needs not be known a priori and no matrix inversion is required.
IEEE Transactions on Systems Man and CyberneticsAn Automatic Clustering Algorithm and Its Properties in High-Dimensional Spaces
28 Citations1972Anthony N. Mucciardi, Earl E. Gose
This paper presents heuristics which were developed to automate the selection of the control parameters and provides a method for determining their value by extrapolation, thereby avoiding a great deal of computation.
IEEE Transactions on Electronic ComputersA Critical Comparison of Two Kinds of Adaptive Classification Networks
26 Citations1965Karl Steinbuch, Bernard Widrow
This report compares the capabilities and equipment requirements of two kinds of adaptive classification networks--the 'Learning Matric,' and the Madaline, and indicates that in most cases the Learning Matrix will require fewer adaptation cycles than will theMadaline when applied to a given problem.
LINGUISTIC METHODS IN PICTURE PROCESSING - A SURVEY *
25 Citations1968W. F. hliller, A. C. Slmw
Communications of the ACMPreliminary investigation of techniques for automated reading of unformatted text
20 Citations1968George Nagy
It will be shown that for the majority of subroutines the method indicated in Remark 5 practically does not increase the complexity of the computation of S~s.
IEEE Transactions on Systems Science and CyberneticsUnsupervised Learning Minimum Risk Pattern Classification for Dependent Hypotheses and Dependent Measurements
14 Citations1969C. Hilborn, D.G. Lainiotis
A recursive Bayes optimal solution is found for the problem of sequential multicategory pattern recognition when unsupervised learning is required and is shown to be realizable in recursive form with fixed memory requirements.
IEEE Transactions on Military ElectronicsA Pattern Recognition Function of Integral Geometry
13 Citations1963G. R. Tenery
It is demonstrated that the transformation yields automatic recognition of general imagery both as to class and as to discrimination between members of the same class.
SIAM ReviewOptical Character Recognition (George L. Fischer, Jr., Donald K. Pollock, Bernard Radack and Mary Elizabeth Stevens, eds.)
6 Citations1964Donald B. Brick