Improved Image Processing Techniques using Multi-level Methods
Speaker: Simon Long, ITEE
When: 2005-07-29 12:00:00
Venue: 78-420
Host: Prof. Brian Lovell
Abstract:Medical imaging is increasingly being used as a diagnostic tool. In
addition, medical imaging devices are improving, leading to
increased imaging resolution and consequently larger datasets, to
which automated image segmentation is often being applied. A great
deal of work has been devoted to improving image segmentation and
image preprocessing algorithms using new methods as well as faster
techniques. Among the successful approaches are Partial
Differential Equation methods, graph-based methods and Active
Contours.
This research aims to produce fast multi-level algorithms for
segmentation and registration that offer major improvements in
efficiency over existing methods. The implementation of algorithms
as multi-resolution methods is already recognised to exhibit less
complexity than those operating on a single resolution. In
particular, multigrid methods are still relatively new to image
processing and there is great scope to introduce them to iterative
approaches that are computationally complex. In this presentation I
will describe multigrid theory and its application to improve
low-level vision problems, discussing results produced for
implemented multigrid diffusion and reaction-diffusion. Finally, I
will present my plan for research that I shall pursue towards the
completion of my dissertation.
Biography:(biography unavailable)
Type: Ph.D confirmation
Contact:Prof. Brian Lovell, seminar host (lovell@itee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)