features
rblanc edited this page Feb 22, 2012
·
3 revisions
- High level: Statismo provides a high level interface to Statistical Models. Statismo lets you work with shapes and images instead of with Eigenvectors and Eigenvalues
- Fully probabilistic: Statismo uses Probabilistic Principal Component Analysis as its underlying model, which gives a fully probabilistic interpretation to statistical shape models.
- Library independent: Statismo can be used with any shape or image library (e.g. vtk, itk, ...), by writing a simple Representer class.
- Reproducible: Statismo stores metadata along with the model data, to make model building reproducible.
- Efficient and flexible storage: Statismo saves the data in HDF5 Format. This allows us to store all the data in a single file, which makes models easy to exchange. Furthermore, as HDF5 is supported by a large number of programs (including Matlab and R), the raw data is easy to access.
- State of the art algorithms: Statismo includes algorithms for building models that are conditioned on further information (such as e.g. known partial shapes or even surrogate variables).
- Eigenfaces for recognition
Turk, M. and Pentland, A.
Journal of cognitive neuroscience, 1991 - Active shape models-their training and application
Cootes, T.F. and Taylor, C.J. and Cooper, D.H. and Graham, J. and others
Computer vision and image understanding, 1995 - A morphable model for the synthesis of 3D faces
Blanz, V. and Vetter, T.
Proceedings of the 26th annual conference on Computer graphics and interactive techniques, 1999 - Probabilistic Modeling and Visualization of the Flexibility in Morphable Models
Luethi, M. and Albrecht, T. and Vetter, T.
Mathematics of Surfaces XIII, 2009 - Conditional variability of statistical shape models based on surrogate variables
Blanc, R. and Reyes, M. and Seiler, C. and Szekely, G.
Medical Image Computing and Computer-Assisted Intervention, 2009