Abstract
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.
Similar content being viewed by others
References
Achim A, Kuruoglu E, Zerubia J (2006) SAR image filtering based on the heavy-tailed Rayleigh model. IEEE Trans Image Process 15(9):2686–2693
Allende H, Galbiati J (2004) A non-parametric filter for digital image restoration, using cluster analysis. Pattern Recognit Lett 25(8):841–847
Allende H, Galbiati J, Vallejos R (1998) Digital image restoration using autoregressive time series type models. Bull Eur Spat Agency 434:53–59
Allende H, Galbiati J, Vallejos R (2001) Robust image modeling on image processing. Pattern Recognit Lett 22(11):1219–1231
Aysal T, Barner K (2006) Quadratic weighted median filters for edge enhancement of noisy images. IEEE Trans Image Process 15(11):3294–3310
Baran S, Pap G, Zuijlen MV (2004) Asymptotic inference for a nearly unstable sequence of stationary spatial AR models. Stat Probab Lett 69(1):53–61
Basu S, Reinsel G (1993) Properties of the spatial unilateral first-order ARMA model. Adv Appl Probab 25(3):631–648
Bhandari A, Kumar A, Singh G (2015) Improved knee transfer function and gamma correction based method for contrast and brightness enhancement of satellite image. Int J Electron Commun 69(2):579–589
Bustos O (1997) Robust statistics in SAR image processing. In: Processing of the first Latino-American seminar on radar remote sensing, pp 81–89
Bustos O, Yohai V (1986) Robust estimates for ARMA models. J Am Stat Assoc 81(393):155–168
Bustos O, Ojeda S, Vallejos R (2009a) Spatial ARMA models and its applications to image filtering. Braz J Probab Stat 23(2):141–165
Bustos O, Ruiz M, Ojeda S, Vallejos R, Frery A (2009b) Asymptotic behavior of RA-estimates in autoregressive 2D processes. J Stat Plan Inference 139(10):3649–3664
Comport A, Marchand E, Chaumette F (2006) Statistically robust 2D visual servoing. IEEE Trans Robot 22(2):415–420
Gottardo R, Raftery A, Yeung KY, Bumgarner R (2006) Bayesian robust inference for differential gene expression in microarrays with multiple samples. Biometrics 62(1):10–18
Hamza A, Krim H (2001) Image denoising: a nonlinear robust statistical approach. IEEE Trans Signal Process 49(12):3045–3054
Huang H, Lee T (2006) Data adaptive median filters for signal and image denoising using a generalized sure criterion. IEEE Signal Process Lett 13(9):561–564
Huber P (1964) Robust estimation of a location parameter. Ann Math Stat 35(1):73–101
Ji Z, Huang Y, Xia Y, Zheng Y (2017) A robust modified gaussian mixture model with rough set for image segmentation. Neurocomputing 266:550–565
Kashyap R, Eom K (1988) Robust image modeling techniques with an image restoration application. IEEE Trans Acoust Speech Signal Process 36(8):1313–1325
Kim J, Han J (2006) Outlier correction from uncalibrated image sequence using the triangulation method. Pattern Recognit 39(3):394–404
Lin T (2007) A new adaptive center weighted median filter for suppressing impulsive noise in images. Inf Sci 177(4):1073–1087
Maronna R, Martin R, Yohai V (2006) Robust statistics. Wiley, Chichester
Martin R (1980) Robust estimation of autoregressive models. In: Brillinger DR, Tiao GC (eds) Directions in time series. Institute of Mathematical Statistics, Haywood, pp 228–262
Muler N, Peña D, Yohai V (2009) Robust estimation for ARMA models. Ann Stat 37(2):816–840
Ojeda S (1999) Robust RA estimators for bidimensional autoregressive models. PhD thesis, Universidad Nacional de Córdoba
Ojeda S, Vallejos R, Lucini M (2002) Performance of robust RA estimator for bidimensional autoregressive models. J Stat Comput Simul 72(1):47–62
Ojeda S, Vallejos R, Bustos O (2010) A new image segmentation algorithm with applications to image inpainting. Comput Stat Data Anal 54(9):2082–2093
Ojeda S, Vallejos R, Lamberti P (2012) Measure of similarity between images based on the codispersion coefficient. J Electron Imaging 21(2):023019
Ojeda S, Britos G, Vallejos R (2018) An image quality index based on coefficients of spatial association with an application to image fusion. Spat Stat 23:1–16
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 383–390
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):30–45
Ponomarenko N, Jin L, Ieremeiev O, Lukin V, Egiazarian K, Astola J, Vozel B, Chehdi K, Carli M, Battisti F, Kuo CJ (2015) Image database TID2013: peculiarities, results and perspectives. Signal Process Image Commun 30:57–77
Prastawa M, Bullitt E, Ho S, Gerig G (2004) A brain tumor segmentation framework based on outlier detection. Med Image Anal 8(3):275–283
Quintana C, Ojeda S, Tirao G, Valente M (2011) Mammography image detection processing for automatic micro-calcification recognition. Chil J Stat 2(2):69–79
R Core Team (2017) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. https://www.R-project.org/
Sadabadi M, Shafiee M, Karrari M (2009) Two-dimensional ARMA model order determination. ISA Trans 48(3):247–253
Schabenberger O, Gotway C (2005) Statistical methods for spatial data analysis. Chapman and Hall/CRC, Boca Raton
Singh M, Arora H, Ahuja N (2004) A robust probabilistic estimation framework for parametric image models. Comput Vis ECCV 2004:508–522
Tarel J, Ieng S, Charbonnier P (2002) Using robust estimation algorithms for tracking explicit curves. Comput Vis ECCV 2002:492–507
Theodoridis S, Koutroumbas K (2003) Pattern recognition. Elsevier, Burlington
Tjøstheim D (1978) Statistical spatial series modelling. Adv Appl Probab 10(1):130–154
Vallejos R, García-Donato G (2006) Bayesian analysis of contaminated quarter plane moving average models. J Stat Comput Simul 76(2):131–147
Vallejos R, Mardesic T (2004) A recursive algorithm to restore images based on robust estimation of NSHP autoregressive models. J Comput Graph Stat 13(3):674–682
Wang Z, Bovik A (2002) A universal image quality index. IEEE Signal Process Lett 9(3):81–84
Whittle P (1954) On stationary processes in the plane. Biometrika 41:434–449
Yao Q, Brockwell P (2006) Gaussian maximum likelihood estimation for ARMA models II: spatial processes. Bernoulli 12(3):403–429
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 1–4
Acknowledgements
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.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Britos, G.M., Ojeda, S.M. Robust estimation for spatial autoregressive processes based on bounded innovation propagation representations. Comput Stat 34, 1315–1335 (2019). https://doi.org/10.1007/s00180-018-0845-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-018-0845-4