A class of multiresolution stochastic models generating self-affine images

Fractal image compression is based on the rather poorly motivated assumption that "natural" images exhibit significant affine self-similarity. The accuracy of this assumption is evaluated by a comparison between the statistics of natural images and those of a multiresolution stochastic mod...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on signal processing 1999-06, Vol.47 (6), p.1739-1742
Hauptverfasser:	Wohlberg, B., de Jager, G.
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptive filters Applied sciences Exact sciences and technology Fractal analysis Fractals Higher order statistics Image coding Image compression Image generation Image processing Image resolution Information, signal and communications theory Self-similarity Signal processing Signal processing algorithms Signal resolution Statistics Stochastic processes Stochasticity Telecommunications and information theory Wavelet transforms
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Fractal image compression is based on the rather poorly motivated assumption that "natural" images exhibit significant affine self-similarity. The accuracy of this assumption is evaluated by a comparison between the statistics of natural images and those of a multiresolution stochastic model designed to generate images exhibiting affine self-similarity as assumed by fractal coding techniques. These comparisons suggest that self-affinity does not represent a particularly accurate characterization of image statistics.
ISSN:	1053-587X 1941-0476
DOI:	10.1109/78.765153