Robustifying Vector Median Filter

This paper describes two methods for impulse noise reduction in colour images that outperform the vector median filter from the noise reduction capability point of view. Both methods work by determining first the vector median in a given filtering window. Then, the use of complimentary information from componentwise analysis allows to build robust outputs from more reliable components. The correlation among the colour channels is taken into account in the processing and, as a result, a more robust filter able to process colour images without introducing colour artifacts is obtained. Experimental results show that the images filtered with the proposed method contain less noisy pixels than those obtained through the vector median filter. Objective measures demonstrate the goodness of the achieved improvement.

[1]  Samuel Morillas,et al.  Isolating impulsive noise pixels in color images by peer group techniques , 2008, Comput. Vis. Image Underst..

[2]  Samuel Morillas,et al.  Two-step fuzzy logic-based method for impulse noise detection in colour images , 2010, Pattern Recognit. Lett..

[3]  Samuel Morillas,et al.  Fuzzy Peer Groups for Reducing Mixed Gaussian-Impulse Noise From Color Images , 2009, IEEE Transactions on Image Processing.

[4]  Samuel Morillas,et al.  Adaptive Marginal Median Filter for Colour Images , 2011, Sensors.

[5]  Herbert A. David,et al.  Order Statistics , 2011, International Encyclopedia of Statistical Science.

[6]  John W. Tukey,et al.  Nonlinear (nonsuperposable) methods for smoothing data , 1974 .

[7]  Samuel Morillas,et al.  Local self-adaptive fuzzy filter for impulsive noise removal in color images , 2008, Signal Process..

[8]  B. Ripley,et al.  Robust Statistics , 2018, Wiley Series in Probability and Statistics.

[9]  G. Eichmann,et al.  Vector median filters , 1987 .

[10]  Hassan A. Kingravi,et al.  Nonlinear vector filtering for impulsive noise removal from color images , 2007, J. Electronic Imaging.

[11]  Xinghuo Yu,et al.  Geometric Features-Based Filtering for Suppression of Impulse Noise in Color Images , 2009, IEEE Transactions on Image Processing.

[12]  Hong Ren Wu,et al.  An Adaptive Filter for Image Denoising using Fuzzy Inference , 2003, SIP.

[13]  Hong Ren Wu,et al.  A robust structure-adaptive hybrid vector filter for color image restoration , 2005, IEEE Transactions on Image Processing.

[14]  A. George,et al.  On some results in fuzzy metric spaces , 1994 .

[15]  David Dagan Feng,et al.  Partition-based vector filtering technique for suppression of noise in digital color images , 2006, IEEE Transactions on Image Processing.

[16]  K. Martin,et al.  Vector filtering for color imaging , 2005, IEEE Signal Processing Magazine.

[17]  M. Emre Celebi,et al.  Distance Measures for Reduced Ordering Based Vector Filters , 2009, IET Image Process..

[18]  Panos E. Trahanias,et al.  Generalized multichannel image-filtering structures , 1997, IEEE Trans. Image Process..

[19]  Etienne E. Kerre,et al.  Fuzzy random impulse noise reduction method , 2007, Fuzzy Sets Syst..

[20]  Etienne E. Kerre,et al.  A Fuzzy Noise Reduction Method for Color Images , 2007, IEEE Transactions on Image Processing.

[21]  Panos E. Trahanias,et al.  Directional processing of color images: theory and experimental results , 1996, IEEE Trans. Image Process..

[22]  Andrzej Chydzinski,et al.  Fast detection and impulsive noise removal in color images , 2005, Real Time Imaging.

[23]  Etienne E. Kerre,et al.  A New Fuzzy Color Correlated Impulse Noise Reduction Method , 2007, IEEE Transactions on Image Processing.