Combined higher order non-convex total variation with overlapping group sparsity for impulse noise removal

A typical approach to eliminate impulse noise is to use the ℓ 1 -norm for both the data fidelity term and the regularization terms. However, the ℓ 1 -norm tends to over penalize signal entries which is one of its underpinnings. Hence, we propose a variational model that uses the non-convex ℓ p -norm...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Multimedia tools and applications 2021-05, Vol.80 (12), p.18503-18530
Hauptverfasser:	Adam, Tarmizi, Paramesran, Raveendran, Mingming, Yin, Ratnavelu, Kuru
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Computer Communication Networks Computer Science Data Structures and Information Theory Image restoration Iterative methods Multimedia Information Systems Noise Noise reduction Regularization Signal to noise ratio Special Purpose and Application-Based Systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A typical approach to eliminate impulse noise is to use the ℓ 1 -norm for both the data fidelity term and the regularization terms. However, the ℓ 1 -norm tends to over penalize signal entries which is one of its underpinnings. Hence, we propose a variational model that uses the non-convex ℓ p -norm, 0 < p
ISSN:	1380-7501 1573-7721
DOI:	10.1007/s11042-021-10583-y