Simulation of process of forming the language for description and analysis of the forms of images

doi:10.1016/0031-3203(72)90022-2

Pattern Recognition

Volume 4, Issue 1, January 1972, Pages 101-140

https://doi.org/10.1016/0031-3203(72)90022-2 Get rights and content

Abstract

The theme of this paper is a linguistic approach to the problem of pictorial pattern recognition. Instead of the vocabulary of primitives and grammar being selected by the designer, this new pattern-recognition system is able to make a new description, give the vocabulary, and construct the grammar. The vocabulary consists in two kinds of words, “forms” of characteristic fragments of pictorial patterns (images) and “locations” of these fragments. The enumeration of the forms and locations describes a pattern. The general scheme of the process of forming the language, the ways of extracting the characteristic fragments, the vectors (sentences) connecting “forms” and “location”, and the algorithms for constructing and comparing the image descriptions are described. Simulation of forming a description language and analysis of various forms are presented.

References (24)

M.A. Aiserman et al.
Theoretical basis of the method of potential functions in the problem of teaching automata to separate input situations into classes
Automation and Remote Control
(1964)
O.A. Bashkirov et al.
Algorithms for teaching machines to recognize pictures based on the usage of potential functions
Automation and Remote Control
(1964)
V.L. Brailovsky
On a method for the recognition of plants described by several parameters, and its applications
Automation and Remote Control
(1962)
V.A. Kovalevsky
The correlation method of image recognition
Zh. Vychisl Matem. Fiziki
(1962)
R.A. Nashlyunas
Analytical estimate of the reliability of the correlation method of image recognition
M.I. Shlesinger et al.
On the construction of prototypes for correlation reading automata
M.M. Bongard
The Recognition Problem
(1967)
A.C. Vasmut et al.
Automatication of the process of reading cartographical information
Goedesy and Cartography
(1970)
N.B. Savalishin
A hypothesis on the distribution of points of fixation during observation of images
Automation and Remote Control
(1968)
N.B. Savalishin et al.
Linguistic (structural) approach to the pattern recognition problem (Review)
Automation and Remote Control
(1969)

V.A. Kovalevsky

A sequential optimization in problems of recognition and description of images compendium

Recognition of Pictures and Constructioh of Reading Automata

(1967)

I.B. Muchnik

Local characteristic formation algorithms for visual patterns

Automation and Remote Control

(1966)

Cited by (7)

Primitive pattern learning
1992, Pattern Recognition
A new approach to the feature detection problem, i.e. learning “useful” primitive features from raw images, is proposed. The “useful” features are defined within the training environment as those that allow the learning agent (learning system) to form object representations sufficient for subsequent object recognition. In other words, the “useful” features detected are discriminating, useful features.
What is distance and why do we need the metric model for pattern learning?
1992, Pattern Recognition
The concept of distance, its role in pattern recognition, and some advantages of the new model for pattern learning proposed recently by the author are discussed. The universality, flexibility, and the ability to connect intrinsically the low-level process that selects the primitives for the pattern representation with the higher level recognition process make the model clearly superior to other models proposed so far. The fundamentally new analytical feature of the model, which allows the learning machine to reconfigure itself efficiently, is the introduction of continuity in the classical discrete computational model.
On the foundations of intelligent processes-I. An evolving model for pattern learning
1990, Pattern Recognition
A general adaptive model unifying existing models for pattern learning is proposed. The model, in addition to preserving the merits of geometric and syntactic approaches to pattern recognition, has decisive advantages over them. It can be viewed as a far-reaching generalization of the perceptron, or neural net, models, in which the vector representation and the associated vector operations are replaced by more general structural representation and the corresponding structural operations. The basis of the model is the concept of a transformation system, which is a generalization of Thue (Post-production) systems. Parametric distance functions in transformation systems are introduced. These are generalizations of weighted Levenshtein (edit) distances to more general structured objects. Learning model for transformation systems, unifying many existing models (including that of neural nets), is proposed. The model also suggests how various propositional object (class) descriptions might be generated based on the outputs of the learning processes: these descriptions represent “translation” of some information encoded in the nonpropositional “language” of the corresponding transformation system, representing the environment, into the chosen logical (propositional) language, whose semantics is now defined by the “translation”. In the light of the metric model the intelligence emerges as based on simple arithmetic processes: first, those related to the optimal distance computation, and, second, “counting” and comparing the results of counting for various “important” features, detected at the learning stage (arithmetic predicates).
Chapter 3 Languages for Pattern Description
1974, Mathematics in Science and Engineering
This chapter discusses the languages for pattern description. The first step in formulating a syntactic model for pattern description is the determination of a set of primitives, in terms of which the patterns of interest may be described. This determination will be largely influenced by the nature of the data, the specific application in question, and the technology available for implementing the system. There is no general solution for the primitive selection problem. In recognition of the program, a comparison or match is made between the statement or coded string, describing the unknown pattern and the statements, along with the name of the patterns they describe already stored within the computer. It is found that to reduce the search time the stored statements are examined and arranged into groups, according to some common feature. The criterion for a successful match is that there must be a certain measure of agreement between the unknown statement and the statement, referring to the pattern with which it is to be identified.
Automatic Recognition of Handprinted Characters—The State of the Art
1980, Proceedings of the IEEE
Linguistic analysis of experimental curves
1979, Proceedings of the IEEE

View all citing articles on Scopus

View full text

Simulation of process of forming the language for description and analysis of the forms of images

Abstract

Theoretical basis of the method of potential functions in the problem of teaching automata to separate input situations into classes

Automation and Remote Control

Algorithms for teaching machines to recognize pictures based on the usage of potential functions

Automation and Remote Control

On a method for the recognition of plants described by several parameters, and its applications

Automation and Remote Control

The correlation method of image recognition

Zh. Vychisl Matem. Fiziki

Analytical estimate of the reliability of the correlation method of image recognition

On the construction of prototypes for correlation reading automata

The Recognition Problem

Automatication of the process of reading cartographical information

Goedesy and Cartography

A hypothesis on the distribution of points of fixation during observation of images

Automation and Remote Control

Linguistic (structural) approach to the pattern recognition problem (Review)

Automation and Remote Control

A sequential optimization in problems of recognition and description of images compendium

Recognition of Pictures and Constructioh of Reading Automata

Local characteristic formation algorithms for visual patterns

Automation and Remote Control