Parallelization of a Blind Deconvolution Algorithm (Postprint)

Often it is of interest to deblur imagery in order to obtain higher-resolution images. Deblurring requires knowledge of the blurring function - information that is often not available separately from the blurred imagery. Blind deconvolution algorithms overcome this problem by jointly estimating both...

Full description

Saved in:
Bibliographic Details
Main Authors: Matson, Charles L, Borelli, Kathy J
Format: Report
Language:English
Subjects:
ALGORITHMS
CONVOLUTION
DEBLURRING
HIGH RESOLUTION
HIGH-PERFORMANCE COMPUTING
MULTI-FRAME BLIND DECONVOLUTION
Numerical Mathematics
Optics
PARALLEL PROCESSING
PARALLELIZATION
PE69120G
POSTPRINTS
SYMPOSIA
WUAFRL2304B3AA
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Often it is of interest to deblur imagery in order to obtain higher-resolution images. Deblurring requires knowledge of the blurring function - information that is often not available separately from the blurred imagery. Blind deconvolution algorithms overcome this problem by jointly estimating both the high-resolution image and the blurring function from the blurred imagery. Because blind deconvolution algorithms are iterative in nature, they can take minutes to days to deblur an image depending on how many frames of date are used for the deblurring and the platforms on which the algorithms are executed. Here we present our progress in parallelizing a blind deconvolution algorithm to increase its executions speed. This progress includes sub-frame parallelization and a code structure that is not specialized to a specific computer hardware architecture. Presented at the High-Performance Computing Modernization Users Group Conference, held in Denver, CO, on 26-29 Jun 2006. Published in the Proceedings of the High-Performance Computing Modernization Users Group Conference, 2006. Prepared in collaboration with KJS Consulting, Haiku, HI.