Profile Scale Spaces for Statistical Image Match
Sean Ho, Guido Gerig · 2005
I present a novel image match model for Bayesian segmentation that is statistical, multiscale, and uses a non-Euclidean object-intrinsic coordinate system. The traditional profile model in an Active Shape Model does not take advantage of the expected high degree of correlation between adjacent profiles along the boundary. My new multiscale image match model uses a profile scale space, which blurs along the boundary but not across the boundary. This blurring is done not in Euclidean space but in an object-intrinsic coordinate system provided by the geometric representation of the object. The profile scale space is sampled after the fashion of the Laplacian pyramid; the resulting tree of features is used to build a Markov Random Field probability distribution for Bayesian image match. Results are shown on a large dataset of 114 segmented caudates in T1-weighted magnetic resonance images (MRI). The image match model is evaluated on the basis of generalizability, specificity, and variance; it is compared against the traditional single-scale profile model. Tests also evaluate whether automatic segmentations using my new multiscale image match model instead of the traditional single-scale profile model come closer to the results of manual segmentation.