Point estimation for multi-spectral distributed random matrices

DOI10.1016/J.LAA.2008.06.034MaRDI QIDQ1017617zbMATH OpenOpenAlexFDO

Authors J. Martínez

Publication date 12 May 2009

Published in Linear Algebra and its Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.laa.2008.06.034

zbMATH Keywords

covariance matrixmaximum likelihood estimationmean vectormultivariate normal distributionnoised imagesnumerical experimentrandom matricessignal

Mathematics Subject Classification ID

Random matrices (algebraic aspects) (15B52) Analysis of variance and covariance (ANOVA) (62J10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Review text

The authors propose a method for better recognition of noised images. The image vector is assumed to be normal \((M,\Sigma)\) and presents a sum of independent normal signal vectors with unknown mean and covariance matrix and a noise vector with zero mean and known covariance matrix. It is assumed that the problem of signals from noise separation may be solved by one of methods cited. Theorems 1-5 present maximum likelihood estimators for \(M\) and \(\Sigma\) and of signal distribution parameters. A numerical experiment of ten digits recognition from noised patterns shows the advantage of the maximum likelihood prognoses over human eye recognition.

Recommendations

• A generalized maximum pseudo-likelihood estimator for noisy Markov fields
• Estimation of parameters for normally distributed random matrices
• Identification and restoration of noisy blurred images using the expectation-maximization algorithm
• scientific article; zbMATH DE number 910669
• On the problem of stable image restoration

Cites work

• Cross-Validatory Estimation of the Number of Components in Factor and Principal Components Models
• Estimation of parameters for normally distributed random matrices
• Fourth-order properties of normally distributed random matrices
• scientific article; zbMATH DE number 3886886 (Why is no real title available?)
• Linear Statistical Inference and its Applications
• On the maximum likelihood estimation of parameters of a spatial discrimination model
• Transformation of non positive semidefinite correlation matrices

Cited in

(2)

• An estimation approach for Gaussian distribution on degraded images
• A new approach to multiple class pattern classification with random matrices

This page was built for publication: Point estimation for multi-spectral distributed random matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1017617)