Image processing through multiscale analysis and measurementnoise modeling

  • Authors:
  • F. Murtagh;J.-L. Starck

  • Affiliations:
  • School of Computer Science, The Queen's University of Belfast, Belfast BT7 1NN, Northern Ireland;DAPNIA/SEI-SAP, CEA-Saclay, F-91191 Gif-sur-Yvette Cedex, France

  • Venue:
  • Statistics and Computing
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

We describe a range of powerful multiscale analysis methods.We also focus on the pivotal issue of measurement noise in thephysical sciences. From multiscale analysis and noise modeling, wedevelop a comprehensive methodology for data analysis of2D images, 1D signals (or spectra), and pointpattern data. Noise modeling is based on the following: (i) multiscaletransforms, including wavelet transforms; (ii) a data structure termed themultiresolution support; and (iii) multiple scale significancetesting. The latter two aspectsserve to characterize signal with respect to noise.The data analysis objectives we deal with include noise filteringand scale decomposition for visualization or feature detection.