We propose a new space-variant regularisation term for variational image restoration based on the assumption that the gradient magnitudes of the target image distribute locally according to a half-Generalised Gaussian distribution. This leads to a highly flexible regulariser characterised by two per-pixel free parameters, which are automatically estimated from the observed image. The proposed regulariser is coupled with either the L2 or the L1 fidelity terms, in order to effectively deal with additive white Gaussian noise or impulsive noises such as, e.g. additive white Laplace and salt and pepper noise. The restored image is efficiently computed by means of an iterative numerical algorithm based on the alternating direction method of multipliers. Numerical examples indicate that the proposed regulariser holds the potential for achieving high-quality restorations for a wide range of target images characterised by different gradient distributions and for the different types of noise considered.

Space-variant Generalised Gaussian Regularisation for Image Restoration

Lanza, A.;Morigi, S.;PRAGLIOLA, MONICA;Sgallari, F.
2019

Abstract

We propose a new space-variant regularisation term for variational image restoration based on the assumption that the gradient magnitudes of the target image distribute locally according to a half-Generalised Gaussian distribution. This leads to a highly flexible regulariser characterised by two per-pixel free parameters, which are automatically estimated from the observed image. The proposed regulariser is coupled with either the L2 or the L1 fidelity terms, in order to effectively deal with additive white Gaussian noise or impulsive noises such as, e.g. additive white Laplace and salt and pepper noise. The restored image is efficiently computed by means of an iterative numerical algorithm based on the alternating direction method of multipliers. Numerical examples indicate that the proposed regulariser holds the potential for achieving high-quality restorations for a wide range of target images characterised by different gradient distributions and for the different types of noise considered.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/642211
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact