Bayesian Spherical Wavelet Shrinkage: Applications to Shape Analysis
Le Faucheur, Xavier
Tannenbaum, Allen R.
MetadataShow full item record
Multiscale analysis has become a very useful tool in image processing and computer vision. Our work is motivated by the need to efficiently represent 3D shapes that exhibit a spherical topology. This note presents a wavelet based model for shape denoising and data compression. The 3D shape signal is first encoded using biorthogonal spherical wavelet functions defined a 3D triangulated mesh. We propose a Bayesian thresholding model for this type of second generation wavelet in order to eliminate wavelet coefficients that are considered as noise. This way, we are able to reduce dimension without losing significant information by estimating a noiseless version of our shape.