Masses of Negative Multinomial Distributions: Application to Polarimetric Image Processing

Masses of Negative Multinomial Distributions: Application to Polarimetric Image Processing

This paper derives new closed-form expressions for the masses of negative multinomial distributions. These masses can be maximized to determine the maximum likelihood estimator of its unknown parameters. An application to polarimetric image processing is investigated. We study the maximum likelihood...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Probability and Statistics 2013-01, Vol.2013 (2013), p.21-33
Hauptverfasser: Bernardoff, Philippe, Tourneret, Jean-Yves, Chatelain, Florent
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Artificial Intelligence
Binomial distribution
Computer Science
Computer Vision and Pattern Recognition
Distribution (Probability theory)
Economic models
Exact solutions
Graphics
Image Processing
Mathematical analysis
Mathematical research
Maximum likelihood estimators
Polarization
Signal and Image Processing
Statistics
Studies
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper derives new closed-form expressions for the masses of negative multinomial distributions. These masses can be maximized to determine the maximum likelihood estimator of its unknown parameters. An application to polarimetric image processing is investigated. We study the maximum likelihood estimators of the polarization degree of polarimetric images using different combinations of images.
ISSN:1687-952X
1687-9538
DOI:10.1155/2013/170967