Analysis of stochastic automata algorithm for relaxation labelling

A parallel stochastic algorithm for relaxation labeling is analyzed. For the case of symmetric compatibility functions, it is proved that time algorithm will always converge to a consistent labeling.< >

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 16; H. 5; S. 538 - 543
Hauptverfasser: Sastry, P.S., Thathachar, M.A.L.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Los Alamitos, CA IEEE 01.05.1994
IEEE Computer Society
Schlagworte:
Algorithm design and analysis
Applied sciences
Artificial intelligence
Computer science; control theory; systems
Computer vision
Convergence
Exact sciences and technology
Image converters
Iterative algorithms
Labeling
Learning automata
Machine intelligence
Pattern recognition. Digital image processing. Computational geometry
Stochastic processes
Learning
Relaxation
Computer vision
Parallel algorithm
Learning automata
Constraint satisfaction
Stochastic algorithm
ISSN:0162-8828
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A parallel stochastic algorithm for relaxation labeling is analyzed. For the case of symmetric compatibility functions, it is proved that time algorithm will always converge to a consistent labeling.< >
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0162-8828
DOI:10.1109/34.291442