Lfc. Pessoa et P. Maragos, MRL-FILTERS - A GENERAL-CLASS OF NONLINEAR-SYSTEMS AND THEIR OPTIMAL-DESIGN FOR IMAGE-PROCESSING, IEEE transactions on image processing, 7(7), 1998, pp. 966-978
Citations number
17
Categorie Soggetti
Computer Science Software Graphycs Programming","Computer Science Theory & Methods","Engineering, Eletrical & Electronic","Computer Science Software Graphycs Programming","Computer Science Theory & Methods
In this paper, the class of morphological/rank/linear (MRL)-filters is
presented as a general nonlinear tool for image processing. They cons
ist of a linear combination between a morphological/rank filter and a
linear filter. A gradient steepest descent method is proposed to optim
ally design these filters, using the averaged least mean squares (LMS)
algorithm. The filter design is viewed as a learning process, and con
vergence issues are theoretically and experimentally investigated. A s
ystematic approach is proposed to overcome the problem of nondifferent
iability of the nonlinear filter component and to improve the numerica
l robustness of the training algorithm, which results in simple traini
ng equations. Image processing applications in system identification a
nd image restoration are also presented, illustrating the simplicity o
f training MRL-filters and their effectiveness for image/signal proces
sing.