Outlier robust corner-preserving methods for reconstructing noisy images

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 comer-preserving properties and outlier robustness. To identify edge-and comer-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.

[1]  Sanford Weisberg,et al.  Computing science and statistics : proceedings of the 30th Symposium on the Interface, Minneapolis, Minnesota, May 13-16, 1998 : dimension reduction, computational complexity and information , 1998 .

[2]  F. Hampel.  A General Qualitative Definition of Robustness , 1971 .

[3]  M. Riedel.  Comparison of Break Points of Estimators , 1984 .

[4]  Peter J. Rousseeuw,et al.  Robust Regression and Outlier Detection , 2005, Wiley Series in Probability and Statistics.

[5]  E. Shikin,et al.  Handbook and atlas of curves , 1995 .

[6]  Brenton R. Clarke,et al.  TRIMMED LIKELIHOOD ESTIMATION OF LOCATION AND SCALE OF THE NORMAL DISTRIBUTION , 1993 .

[7]  M. Hillebrand,et al.  On consistency of redescending M-kernel smoothers , 2006 .

[8]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[9]  I. Johnstone,et al.  Wavelet Shrinkage: Asymptopia? , 1995 .

[10]  Azriel Rosenfeld,et al.  Robust regression methods for computer vision: A review , 1991, International Journal of Computer Vision.

[11]  Werner A. Stahel,et al.  Robust Statistics: The Approach Based on Influence Functions , 1987 .

[12]  Location estimators based on linear combinations of modified order statistics , 1976 .

[13]  E. Candès,et al.  Ridgelets: a key to higher-dimensional intermittency? , 1999, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[14]  J. Marron,et al.  Edge-Preserving Smoothers for Image Processing , 1998 .

[15]  Inge Koch,et al.  On the asymptotic performance of median smoothers in image analysis and nonparametric regression , 1996 .

[16]  B. Price,et al.  Robust Planning and Analysis of Experiments , 1997 .

[17]  D. Donoho.  Wedgelets: nearly minimax estimation of edges , 1999 .

[18]  C. Müller,et al.  Breakdown points and variation exponents of robust $M$-estimators in linear models , 1999 .

[19]  Martin Hillebrand.  On robust corner preserving smoothing in image processing , 2003 .

[20]  Stefan Van Aelst,et al.  Positive-Breakdown Robust Methods in Computer Vision , 1999 .

[21]  J. Polzehl,et al.  Adaptive weights smoothing with applications to image restoration , 1998 .

[22]  J. Polzehl,et al.  Image denoising: Pointwise adaptive approach , 2003 .

[23]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .

[24]  Christine H. Müller.  Comparison of high-breakdown-point estimators for image denoising , 2002 .

[25]  Christine H. Müller.  Robust estimators for estimating discontinuous functions , 2002 .