We represent a shape representation technique using the eigenfunctions of Laplace-Beltrami operator and compare the performance with the conventional spherical harmonic (SPHARM) representation. Cortical manifolds are represented as a linear combination of the Laplace-Beltrami eigenfunctions, which form orthonormal basis. Since the Laplace-Beltrami eigenfunctions reflect the intrinsic geometry of the manifolds, the new representation is supposed to more compactly represent the manifolds and

more »

... rform SPHARM representation. However, this is not demonstrated yet in brain imaging data. We demonstrate the superior reconstruction capability of the Laplace-Beltrami eigenfunction representation using cortical and amygdala surfaces as examples.