Titlebook: Information Processing in Medical Imaging; 19th International C Gary E. Christensen,Milan Sonka Conference proceedings 2005 Springer-Verlag

Gesture

Robust Active Appearance Model Matchingf the matching procedure is demonstrated on a variety of examples with different noise conditions. The proposed algorithm outperformed the conventional AAM matching on images with gross disturbances and can tolerate up to 40% of disturbed data.

松軟無力

減去

Maximum Entropy Spherical Deconvolution for Diffusion MRItion. Experiments compare the new method to linear spherical deconvolution, used previously in diffusion MRI, and to the PASMRI algorithm. The new method compares favourably both in simulation and on standard brain-scan data.