Automatic compression for image sets using a graph theoretical framework
Date
2007
Authors
Gergel, Barry
University of Lethbridge. Faculty of Arts and Science
Journal Title
Journal ISSN
Volume Title
Publisher
Lethbridge, Alta. : University of Lethbridge, Faculty of Arts and Science, 2007
Abstract
A new automatic compression scheme that adapts to any image set is presented in this thesis.
The proposed scheme requires no a priori knowledge on the properties of the image
set. This scheme is obtained using a unified graph-theoretical framework that allows for
compression strategies to be compared both theoretically and experimentally. This strategy
achieves optimal lossless compression by computing a minimum spanning tree of a
graph constructed from the image set. For lossy compression, this scheme is near-optimal
and a performance guarantee relative to the optimal one is provided. Experimental results
demonstrate that this compression strategy compares favorably to the previously proposed
strategies, with improvements up to 7% in the case of lossless compression and 72% in
the case of lossy compression. This thesis also shows that the choice of underlying compression
algorithm is important for compressing image sets using the proposed scheme.
Description
x, 77 leaves ; 29 cm.
Keywords
Dissertations, Academic , Data compression (Computer science) , Graph theory -- Data processing