|Stochastic Systems Group|
Dr. Nikos Paragios
Imaging and Visualization Department
Siemens Corporate Research
Level Set Representations, the pioneering framework introduced by Osher and Sethian (1988) is the most common choice for the implementation of variational frameworks in Computer Vision since it is implicit, intrinsic, parameter and topology free. However, many computer vision applications refer to entities with physical meanings that follow a shape form with a certain degree of variability. In this talk, we propose a three-stage contribution. First, we will introduce a novel alignment method for the matching of geometric shapes that exploits maximally the characteristics of these representations. Then, based on the set of aligned training samples we will propose a novel variational method for the construction of a level set shape prior model. These two components will be used within an energetic formulation to introduce shape constraints to level set representations. This formulation exploits all advantages of these representations resulting on a very elegant approach that can deal with a large number of parametric as well as continuous transformations of the model. Furthermore, it can be combined with existing well-known level set-based segmentation approaches leading to paradigms that can deal with noisy, occluded and missing or physically corrupted data. Encouraging experimental results are obtained using synthetic and real images. If time permits, the application of the Segmentation of the Left Ventricle will be considered to demonstrate the efficiency of the proposed method.
Problems with this site should be emailed to firstname.lastname@example.org