On the statistics of natural stochastic textures and their application in image processing

Statistics of natural images has become an important subject of research in recent years. The highly kurtotic, non-Gaussian, statistics known to be characteristic of many natural images are exploited in various image processing tasks. In this paper, we focus on natural stochastic textures (NST) and...

Full description

Saved in:
Bibliographic Details
Main Authors: Zachevsky, Ido, Zeevi, Yehoshua Y.
Format: Conference Proceeding
Language:English
Subjects:
denoising
fractional Brownian motion
Gaussian distribution
Image resolution
Image texture enhancement
natural image statistics
Noise reduction
PSNR
self-similarity
Signal resolution
Stochastic processes
superresolution
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Statistics of natural images has become an important subject of research in recent years. The highly kurtotic, non-Gaussian, statistics known to be characteristic of many natural images are exploited in various image processing tasks. In this paper, we focus on natural stochastic textures (NST) and substantiate our finding that NST have Gaussian statistics. Using the well-known statistical self-similarity property of natural images, exhibited even more profoundly in NST, we exploit a Gaussian self-similar process known as the fractional Brownian motion, to derive a fBm-PDE-based singleimage superresolution scheme for textured images. Using the same process as a prior, we also apply it in denoising of NST.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2014.6854721