Abstract

The object of this paper is to present aform ulation for thesegmF tation and restorationproblem using flexiblem dels with a robust regularized network (RRN). A two-steps iterativealgorithm is presented. In the first step an approximoh-- of the classification iscomJq-( by using a localmh)q)F)hfl-5 algorithm and in the second step the param-5hfl of the RRN are updated. The use of robust potentials ismh)N ated by (a) classification errors that can resultfrom the use of localmlh))FfiE algorithm in theimh-fiF) tation, and (b) the need to adapt the RN using localimhgradientinformfl -fi) to imfiE ve fidelity of them odel to the data.

Citations