Abstract:
The success of medical image de-noising often relies on the image quality. If the image is severely degraded, information can be permanently lost. The de-noising or resto...Show MoreMetadata
Abstract:
The success of medical image de-noising often relies on the image quality. If the image is severely degraded, information can be permanently lost. The de-noising or restoration process rarely use any other external information such as valuable data from additional images, for instance from a follow-up study or within an image sequence. Several optimization methods exist, among them the Graph Cuts method is efficient in a global optimum sense. We show that Graph Cuts can be used to solve simultaneously image de-noising and image correspondence. Both of these problems have been previously solved with Graph Cuts, but always as separate processes. In this paper, we combine them in the same formulation, and we show an application where images, initially unusable, can be recovered rather than being reacquired at a high risk (e.g., avoiding new radiation in medical scans).
Published in: 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)
Date of Conference: 02-05 July 2012
Date Added to IEEE Xplore: 24 September 2012
ISBN Information: