Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP

Heike Hufnagel, Xavier Pennec, Jan Ehrhardt, Heinz Handels, Nicholas Ayache


A fundamental problem when computing statistical shape models (SSMs) is the determination of correspondences between the instances. Often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variation results. We present a novel algorithm based on the affine Expectation Maximization - Iterative Closest Point (EM-ICP) registration method. Exact correspondences are replaced by iteratively evolving correspondence probabilities which provide the basis for the computation of mean shape and variability model. We validated our approach by computing SSMs using inexact correspondences for kidney and putamen data. In ongoing work, we want to use our methods for automatic classification applications.

Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2007
Number of pages5
Place of PublicationBerlin, Heidelberg
PublisherSpringer Verlag
Publication date01.12.2007
ISBN (Print)978-3-540-71090-5
ISBN (Electronic)978-3-540-71091-2
Publication statusPublished - 01.12.2007
EventWorkshop on Bildverarbeitung fur die Medizin 2007 - Munich, Germany
Duration: 25.03.200727.03.2007
Conference number: 97564


Dive into the research topics of 'Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP'. Together they form a unique fingerprint.

Cite this