Discontinuity-Preserving Vector Smoothing of Multivariate MR Images Using Vector Mean Field Annealing

Authors:
Youn-Sik Han;Wesley E. Snyder;Griff L. Bilbro
Affiliations:
Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC;Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC;Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC
Venue:
Journal of Mathematical Imaging and Vision
Year:
1998

Citing 9
Cited 0

Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Range image restoration using mean field annealing

Advances in neural information processing systems 1
Biased anisotropic diffusion: a unified regularization and diffusion approach to edge detection

Image and Vision Computing - Special issue on the first ECCV 1990
Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Smoothing: A General Tool for Early Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Energy minimization approach to motion estimation

Signal Processing - Special issue on multidimensional signal processing
Magnetic resonance image restoration

Journal of Mathematical Imaging and Vision
The effects of various basis image priors on MR image MAP restoration

Journal of Mathematical Imaging and Vision
Image Relaxation: Restoration and Feature Extraction

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider PD-, T1-, and T2-weighted magnetic resonance images jointly as a vector-valued image and use the angle of this vector field to formulate maximum a posteriori restoration as a global optimization problem. We use Mean Field Annealing (MFA) to find restorations that are superior to those obtained by previous multivariate approaches when shading artifacts near the MRI antenna are significant. Local homogeneity of thevector field as well as the angle between the components or the ratio of the components of the field are shown to have potential use for improving segmentation.