Breadcrumb
Multiscale Methods
In recent years multiscale methods have revolutionised the modelling and analysis of phenomena in a number of different disciplines. The `multiscale' paradigm typically involves a multiscale representation and then manipulation of that representation to achieve a desired goal.
The FBI fingerprint database uses multiscale methods.
Practical applications include: modelling communications network traffic - such as queues on routers - and image compression. The JPEG 2000 standard is based on wavelet compression. So is the FBI fingerprint database.
Ongoing projects
- "Haar-Fisz and wavelet-Fisz estimation techniques in locally stationary time series models" by Piotr Fryzlewicz, Guy Nason and Suhasini Subba Rao, with Rainer von Sachs and Theofanis Sapatinas.
Recent publications
-
A statistical multiscale approach to image segmentation and fusion (2005)
Cardinali, A. and Nason, G.P.
Proceedings of the Eighth International Conference on Information Fusion
URL provided by the author