Robust estimation for spatial autoregressive processes based on bounded innovation propagation representations
- 167 Downloads
Robust methods have been a successful approach for dealing with contamination and noise in the context of spatial statistics and, in particular, in image processing. In this paper, we introduce a new robust method for spatial autoregressive models. Our method, called BMM-2D, relies on representing a two-dimensional autoregressive process with an auxiliary model to attenuate the effect of contamination (outliers). We compare the performance of our method with existing robust estimators and the least squares estimator via a comprehensive Monte Carlo simulation study, which considers different levels of replacement contamination and window sizes. The results show that the new estimator is superior to the other estimators, both in accuracy and precision. An application to image filtering highlights the findings and illustrates how the estimator works in practical applications.
KeywordsAR-2D models Robust estimators Image processing Spatial models
We thank Ph.D. Oscar Bustos and Ph.D. Ronny Vallejos for helpful comments and suggestions. The authors were supported by Secyt-UNC grant (Res. Secyt 313/2016.), Argentina. The first author was partially supported by CIEM-CONICET, Argentina.
- Allende H, Galbiati J, Vallejos R (1998) Digital image restoration using autoregressive time series type models. Bull Eur Spat Agency 434:53–59Google Scholar
- Bustos O (1997) Robust statistics in SAR image processing. In: Processing of the first Latino-American seminar on radar remote sensing, pp 81–89Google Scholar
- Martin R (1980) Robust estimation of autoregressive models. In: Brillinger DR, Tiao GC (eds) Directions in time series. Institute of Mathematical Statistics, Haywood, pp 228–262Google Scholar
- Ojeda S (1999) Robust RA estimators for bidimensional autoregressive models. PhD thesis, Universidad Nacional de CórdobaGoogle Scholar
- Pistonesi S, Martinez J, Ojeda S, Vallejos R (2015) A novel quality image fusion assessment based on maximum codispersion. In: Pardo A, Kittler J (eds) Proceedings of the Iberoamerican congress on pattern recognition, pp 383–390Google Scholar
- Ponomarenko N, Lukin V, Zelensky A, Egiazarian K, Carli M, Battisti F (2009) TID2008—a database for evaluation of full-reference visual quality assessment metrics. Adv Mod Radioelectron 10(4):30–45Google Scholar
- R Core Team (2017) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. https://www.R-project.org/
- Zielinski J, Bouaynaya N, Schonfeld D (2010) Two-dimensional ARMA modeling for breast cancer detection and classification. In: Proceedings of the international conference on signal processing and communications. IEEE, pp 1–4Google Scholar