In this seminar, we will discuss a new sparse shape modeling framework on the LB eigenfunctions. To reduce high frequency noise and some lower frequency terms that not necessarily contribute significantly in reconstructing the surfaces, the paper propose to filter out only the significant eigenfunctions by imposing l1-penalty. The experimental results investigate the influence of age and gender on amygdala and hippocampus shapes in the normal population. It also shows how the emotional response is related to the anatomy of the subcortical structures.
S. Kim, M.K. Chung, et al. Sparse Shape Representation using the Laplace-Beltrami Eigenfunctions and Its Application to Modeling Subcortical Structures. MMBIA 2012, pp 25-32.
To download attachments, please log in.