Title :
Median-rational hybrid filters for image restoration
Author :
Khriji, L. ; Gabbouj, M.
Author_Institution :
Signal Process. Lab., Tampere Univ. of Technol., Finland
fDate :
5/14/1998 12:00:00 AM
Abstract :
A new class of nonlinear filters is introduced, called median-rational hybrid filters (MRHFs), based on rational functions (RFs). The output is the result of rational operation taking into account three sub-functions. It is shown that every sub-function will preserve details within its sub-windows. The proposed MRHF filters have the inherent property that on smooth areas they provide good noise attenuation whereas on changing areas the noise attenuation is traded for good response to change. It is shown that a consistent reduction in the objectively measured mean absolute error and mean square error is obtained
Keywords :
Gaussian noise; filtering theory; image restoration; median filters; image restoration; mean absolute error reduction; mean square error reduction; median-rational hybrid filters; noise attenuation; nonlinear filters; rational functions; sub-function;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980666