ARFBF model for non stationary random fields and application in HRTEM images

Zhangyun Tan, Abdourrahmane M. Atto, Olivier Alata, Maxime Moreaud

Abstract

This paper presents a new model called Autoregressive Fractional Brownian Field (ARFBF) for analyzing textures which contain stationary and non-stationary components. The paper also proposes two estimation methods for the parameter of an isotropic fractional Brownian field based on Wavelet Packet (WP) spectrum: the Log-Regression on Diagonal WP spectrum (Log-RDWP) and the Log-Regression on Polar representation of WP spectrum (Log-RPWP). The Log-RPWP method provides a better estimation performance for small size images. We show the interest of ARFBF model and Log-RPWP for characterizing High-Resolution Transmission Electron Microscopy (HRTEM) images.
BibTeX
@inproceedings{tan2015arfbf,
  author = {Zhangyun Tan and Abdourrahmane M. Atto and Olivier Alata and Maxime Moreaud},
  title = {{ARFBF model for non stationary random fields and application in HRTEM images}},
  booktitle = {ICIP},
  year = {2015},
  url = {https://openreview.net/forum?id=ZE7nw5ybhT},
}

Loading related content...

Figure