A Navaei wrote: > 2009/2/24 Harish Narayanan <[email protected]>: >> A Navaei wrote: >>> Finally after all those long discussions on the best way of >>> architecturing variational image processing problems based on dolfin, >>> a minimal demo showing how to solve a classical motion estimation PDE >>> is available now -- thanks for all the support. Detailed explanation >>> is given here: >>> >>> http://code.google.com/p/debiosee/wiki/DemosOptiocFlowHornSchunck >> Looks interesting. Are there plans to (or is it straightforward to) >> extend this to other functionals to process the image in other ways? >> (e.g. Edge detection and selective smoothening/sharpening.) > > Both of the good points that you mentioned are part of the main goals > of Debiosee. The project was created with the idea of implementing a > comprehensive set of variational algorithms with applications in image > processing. Anyone interested in such contribution is welcome to join. > > Selecting fenics as the variational engine and itk as the image > processing library, provides a rich combination of tools making it > very likely that you would find the necessary requirement available if > you want to solve a new problem. Moreover, since both libraries come > with excellent rapid prototyping features, eg variational forms in > dolfin or automated template wrapping in itk, developing will be fast > and demands less programming skills. Variational image processing is a > young since, paper [1] is a good introduction to some applications.
Cool. Then I will try some variational shape reconstruction stuff (someday!). _______________________________________________ DOLFIN-dev mailing list [email protected] http://www.fenics.org/mailman/listinfo/dolfin-dev
