This Title All WIREs
How to cite this WIREs title:
WIREs Comp Stat

Scale space methods

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract We discuss methods that use multiscale smoothing for explorative data analysis and inference. The problems considered involve nonparametric density estimation and regression, time series analysis, image analysis, and more general spatial data analysis settings. Copyright © 2010 John Wiley & Sons, Inc. This article is categorized under: Statistical and Graphical Methods of Data Analysis > Statistical Graphics and Visualization

Three slices of a scale space of a rose image.

[ Normal View | Magnified View ]

First row: the reconstructed image difference E (μ|y) of two satellite images (first panel) together with three smooths obtained as posterior means E (Sλμ|y). The effective size of the smoother is indicated by the yellow circle. Second row: credibility maps that show the salient features in different spatial resolutions.

[ Normal View | Magnified View ]

Left panel: the noisy example image. Middle panel: arrows indicate significant gradient direction and different colors flag different types of local curvature. Right hand panel: streamlines computed from significant gradient directions.

[ Normal View | Magnified View ]

BSiZer analysis of a diatom‐ based temperature reconstruction in northern Fennoscandia for the last 800 years. The upper panel: the reconstructed temperatures shown as asterisks together with three smooths obtained as posterior means. The lower panel: BSiZer map with the three smoothing levels shown using the same colors as in the upper panel. For details see Ref 24.

[ Normal View | Magnified View ]

SiZer analysis of the Hidalgo stamp data. In the upper panel several smooths of data are shown and the SiZer map is in the lower panel.

[ Normal View | Magnified View ]

Related Articles

Image restoration

Browse by Topic

Statistical and Graphical Methods of Data Analysis > Statistical Graphics and Visualization

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts