The gamma generalized normal distribution: A descriptor of SAR imagery

Abstract We propose a new four-parameter distribution for modeling synthetic aperture radar (SAR) imagery named the gamma generalized normal (GGN) by combining the gamma and generalized normal distributions. A mathematical characterization of the new distribution is provided by identifying the limiting behavior and by calculating the density and moment expansions. The GGN model performance is evaluated on both synthetic and actual data and, for that, maximum likelihood estimation and random number generation are discussed. The proposed distribution is compared with the beta generalized normal (BGN) distribution, which has already shown to appropriately represent SAR imagery. The performance of these two distributions are measured by means of statistics which provide evidence that the GGN can outperform the BGN distribution in some contexts.

[1]  J. J. Ranjani,et al.  Image Retrieval using Generalized Gaussian Distribution and Score based Support Vector Machine , 2016 .

[2]  Gui Gao,et al.  Statistical Modeling of SAR Images: A Survey , 2010, Sensors.

[3]  D. Kundu,et al.  Theory & Methods: Generalized exponential distributions , 1999 .

[4]  S. Nadarajah.  A generalized normal distribution , 2005 .

[5]  Renato J. Cintra,et al.  Comparing Edge Detection Methods Based on Stochastic Entropies and Distances for PolSAR Imagery , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  Yipeng Li,et al.  Shape Parameter Estimator of the Generalized Gaussian Distribution Based on the MoLC , 2018, IEEE Geoscience and Remote Sensing Letters.

[7]  Djemel Ziou,et al.  Statistical modelling of multimodal SAR images , 2007 .

[8]  F. Famoye,et al.  BETA-NORMAL DISTRIBUTION AND ITS APPLICATIONS , 2002 .

[9]  Ken D. Sauer,et al.  A generalized Gaussian image model for edge-preserving MAP estimation , 1993, IEEE Trans. Image Process..

[10]  Q. Vuong.  Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses , 1989 .

[11]  Dipak K. Dey,et al.  Long-term survival models with latent activation under a flexible family of distributions , 2013 .

[12]  I. J. Taneja.  Bounds On Triangular Discrimination, Harmonic Mean and Symmetric Chi-square Divergences , 2005, math/0505238.

[13]  G. S. Mudholkar,et al.  Exponentiated Weibull family for analyzing bathtub failure-rate data , 1993 .

[14]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[15]  Saralees Nadarajah,et al.  The Exponentiated Gamma Distribution with Application to Drought Data , 2007 .

[16]  Deo Kumar Srivastava,et al.  The exponentiated Weibull family: a reanalysis of the bus-motor-failure data , 1995 .

[17]  Gauss M. Cordeiro,et al.  A new compounding family of distributions: The generalized gamma power series distributions , 2016, J. Comput. Appl. Math..

[18]  Torbjørn Eltoft,et al.  Automated Non-Gaussian Clustering of Polarimetric Synthetic Aperture Radar Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[19]  D. Blacknell,et al.  Comparison of parameter estimators for K-distribution , 1994 .

[20]  D. Evans,et al.  The Distribution of the Kolmogorov–Smirnov, Cramer–von Mises, and Anderson–Darling Test Statistics for Exponential Populations with Estimated Parameters , 2008 .

[21]  Shun-ichi Amari,et al.  The AIC Criterion and Symmetrizing the Kullback–Leibler Divergence , 2007, IEEE Transactions on Neural Networks.

[22]  G. Cordeiro,et al.  Beta generalized normal distribution with an application for SAR image processing , 2014, 2206.01357.

[23]  R. Garello,et al.  Statistical modelling of ocean SAR images , 1997 .

[24]  F. Famoye,et al.  The beta-Pareto distribution , 2008 .

[25]  B. Efron.  More Efficient Bootstrap Computations , 1990 .

[26]  Pushpa L. Gupta,et al.  Modeling failure time data by lehman alternatives , 1998 .

[27]  S. Loukas,et al.  A lifetime distribution with decreasing failure rate , 1998 .

[28]  Nadine Martin,et al.  Maximum likelihood noise estimation for spectrogram segmentation control , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[29]  Gauss M. Cordeiro,et al.  The exponentiated generalized gamma distribution with application to lifetime data , 2011 .

[30]  K. Lange,et al.  A Theoretical Study of Some Maximum Likelihood Algorithms for Emission and Transmission Tomography , 1987, IEEE Transactions on Medical Imaging.

[31]  Chin-Diew Lai,et al.  Constructions and applications of lifetime distributions , 2013 .

[32]  Narayanaswamy Balakrishnan,et al.  On families of beta- and generalized gamma-generated distributions and associated inference , 2009 .

[33]  Corina da Costa Freitas,et al.  A model for extremely heterogeneous clutter , 1997, IEEE Trans. Geosci. Remote. Sens..

[34]  John C. Nash,et al.  On Best Practice Optimization Methods in R , 2014 .

[35]  N. Balakrishnan,et al.  The gamma-exponentiated exponential distribution , 2012 .

[36]  J. Copas,et al.  Interpreting Kullback-Leibler divergence with the Neyman-Pearson lemma , 2006 .