Outlier robust corner-preserving methods for reconstructing noisy images

Abstract

The ability to remove a large amount of noise and the ability to preserve most structure are desirable properties of an image smoother. Unfortunately, they usually seem to be at odds with each other; one can only improve one property at the cost of the other. By combining M-smoothing and least-squares-trimming, the TM-smoother is introduced as a means to unify corner-preserving properties and outlier robustness. To identify edge- and corner-preserving properties, a new theory based on differential geometry is developed. Further, robustness concepts are transferred to image processing. In two examples, the TM-smoother outperforms other corner-preserving smoothers. A software package containing both the TM- and the M-smoother can be downloaded from the Internet.Comment: Published at http://dx.doi.org/10.1214/009053606000001109 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org

A spatio-spectral hybridization for edge preservation and noisy image restoration via local parametric mixtures and Lagrangian relaxation

“…Reviews of the state of the art techniques for edge and line oriented approaches to contour detection can be seen in [37]. Other edge preserving approaches in image processing have been discussed in literature [11,28] and references therin.…”

Jump Detection In Blurred Regression Surfaces

“…Step 2 of the above procedure, G{f }(x, y) can be constructed by any jump-preserving surface estimator proposed in the literature (see Hillebrand and Müller 2007;Qiu 2007). In all numerical examples presented in this article, the local piecewise constant kernel estimator suggested in Qiu (2009) is used.…”

Application of the partitioning method to specific Toeplitz matrices

“…The recovery of an original image from degraded observations is of crucial importance and finds application in several scientific areas including medical imaging and diagnosis, military surveillance, satellite and astronomical imaging, remote sensing, etc. Expectably, the field of image restoration has been of great interest in the scientific literature (Banham and Katsaggelos, 1997;Chantas et al, 2007;Chountasis et al, 2009a;2010;Hillebrand and Muller, 2007;Schafer et al, 1981). Also, edge preserving regularization methods, in the context of image restoration and denoising, are presented by Prasath (2011).…”