|
Activity Number:
|
58
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 12, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Computing*
|
| Abstract - #300295 |
|
Title:
|
Adaptive Wavelet Graph Model for Bayesian Tomographic Reconstruction
|
|
Author(s):
|
Charles Bouman*+ and Ken Sauer and Thomas Frese
|
|
Affiliation(s):
|
Purdue University and University of Notre Dame and Purdue University
|
|
Address:
|
, West Lafayette , Indiana, IN 47907,
|
|
Keywords:
|
|
|
Abstract:
|
We introduce an adaptive wavelet graph image model applicable to Bayesian tomographic reconstruction and other problems with non-local observations.The proposed model captures coarse-to-fine scale dependencies in the wavelet tree by modeling the conditional distribution of wavelet coefficients, given overlapping windows of scaling coefficients containing coarse scale information. This results in a graph dependency structure which is more general than a quadtree, enabling the model to produce smooth estimates even for simple wavelet bases such as the Haar basis. The inter-scale dependencies of the wavelet graph model are specified using a spatially non-homogeneous Gaussian distribution with parameters at each scale and location. The parameters of this distribution are selected adaptively using nonlinear classification of coarse scale data. The nonlinear adaptation mechanism is based on a set of training images. In conjunction with the wavelet graph model, we present a computationally efficient multiresolution image reconstruction algorithm.This algorithm is based on iterative Bayesian space domain optimization using scale recursive updates of the wavelet graph prior model.
|
