Automatic and robust computation of 3D medial models incorporating object variability

Martin Styner, Guido Gerig, Sarang Joshi, Stephen Pizer

    Research output: Contribution to journalArticle

    Abstract

    This paper presents a novel processing scheme for the automatic and robust computation of a medial shape model, which represents an object population with shape variability. The sensitivity of medial descriptions to object variations and small boundary perturbations are fundamental problems of any skeletonization technique. These problems are approached with the computation of a model with common medial branching topology and grid sampling. This model is then used for a medial shape description of individual objects via a constrained model fit. The process starts from parametric 3D boundary representations with existing point-to-point homology between objects. The Voronoi skeleton of each sampled object boundary is partitioned into non-branching medial sheets and simplified by a novel pruning algorithm using a volumetric contribution criterion. Using the surface homology, medial sheets are combined to form a common medial branching topology. Finally, the medial sheets are sampled and represented as meshes of medial primitives. Results on populations of up to 184 biological objects clearly demonstrate that the common medial branching topology can be described by a small number of medial sheets and that even a coarse sampling leads to a close approximation of individual objects.

    Original languageEnglish (US)
    Pages (from-to)107-122
    Number of pages16
    JournalInternational Journal of Computer Vision
    Volume55
    Issue number2-3
    DOIs
    StatePublished - Nov 2003

    Fingerprint

    Topology
    Sampling
    Processing

    Keywords

    • Medial shape description
    • Medical imaging
    • Shape analysis
    • Skeleton pruning
    • Voronoi skeleton

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Artificial Intelligence
    • Computer Vision and Pattern Recognition

    Cite this

    Automatic and robust computation of 3D medial models incorporating object variability. / Styner, Martin; Gerig, Guido; Joshi, Sarang; Pizer, Stephen.

    In: International Journal of Computer Vision, Vol. 55, No. 2-3, 11.2003, p. 107-122.

    Research output: Contribution to journalArticle

    Styner, Martin ; Gerig, Guido ; Joshi, Sarang ; Pizer, Stephen. / Automatic and robust computation of 3D medial models incorporating object variability. In: International Journal of Computer Vision. 2003 ; Vol. 55, No. 2-3. pp. 107-122.
    @article{3869cc6093fc40c68c10c5ac24029f6c,
    title = "Automatic and robust computation of 3D medial models incorporating object variability",
    abstract = "This paper presents a novel processing scheme for the automatic and robust computation of a medial shape model, which represents an object population with shape variability. The sensitivity of medial descriptions to object variations and small boundary perturbations are fundamental problems of any skeletonization technique. These problems are approached with the computation of a model with common medial branching topology and grid sampling. This model is then used for a medial shape description of individual objects via a constrained model fit. The process starts from parametric 3D boundary representations with existing point-to-point homology between objects. The Voronoi skeleton of each sampled object boundary is partitioned into non-branching medial sheets and simplified by a novel pruning algorithm using a volumetric contribution criterion. Using the surface homology, medial sheets are combined to form a common medial branching topology. Finally, the medial sheets are sampled and represented as meshes of medial primitives. Results on populations of up to 184 biological objects clearly demonstrate that the common medial branching topology can be described by a small number of medial sheets and that even a coarse sampling leads to a close approximation of individual objects.",
    keywords = "Medial shape description, Medical imaging, Shape analysis, Skeleton pruning, Voronoi skeleton",
    author = "Martin Styner and Guido Gerig and Sarang Joshi and Stephen Pizer",
    year = "2003",
    month = "11",
    doi = "10.1023/A:1026378916288",
    language = "English (US)",
    volume = "55",
    pages = "107--122",
    journal = "International Journal of Computer Vision",
    issn = "0920-5691",
    publisher = "Springer Netherlands",
    number = "2-3",

    }

    TY - JOUR

    T1 - Automatic and robust computation of 3D medial models incorporating object variability

    AU - Styner, Martin

    AU - Gerig, Guido

    AU - Joshi, Sarang

    AU - Pizer, Stephen

    PY - 2003/11

    Y1 - 2003/11

    N2 - This paper presents a novel processing scheme for the automatic and robust computation of a medial shape model, which represents an object population with shape variability. The sensitivity of medial descriptions to object variations and small boundary perturbations are fundamental problems of any skeletonization technique. These problems are approached with the computation of a model with common medial branching topology and grid sampling. This model is then used for a medial shape description of individual objects via a constrained model fit. The process starts from parametric 3D boundary representations with existing point-to-point homology between objects. The Voronoi skeleton of each sampled object boundary is partitioned into non-branching medial sheets and simplified by a novel pruning algorithm using a volumetric contribution criterion. Using the surface homology, medial sheets are combined to form a common medial branching topology. Finally, the medial sheets are sampled and represented as meshes of medial primitives. Results on populations of up to 184 biological objects clearly demonstrate that the common medial branching topology can be described by a small number of medial sheets and that even a coarse sampling leads to a close approximation of individual objects.

    AB - This paper presents a novel processing scheme for the automatic and robust computation of a medial shape model, which represents an object population with shape variability. The sensitivity of medial descriptions to object variations and small boundary perturbations are fundamental problems of any skeletonization technique. These problems are approached with the computation of a model with common medial branching topology and grid sampling. This model is then used for a medial shape description of individual objects via a constrained model fit. The process starts from parametric 3D boundary representations with existing point-to-point homology between objects. The Voronoi skeleton of each sampled object boundary is partitioned into non-branching medial sheets and simplified by a novel pruning algorithm using a volumetric contribution criterion. Using the surface homology, medial sheets are combined to form a common medial branching topology. Finally, the medial sheets are sampled and represented as meshes of medial primitives. Results on populations of up to 184 biological objects clearly demonstrate that the common medial branching topology can be described by a small number of medial sheets and that even a coarse sampling leads to a close approximation of individual objects.

    KW - Medial shape description

    KW - Medical imaging

    KW - Shape analysis

    KW - Skeleton pruning

    KW - Voronoi skeleton

    UR - http://www.scopus.com/inward/record.url?scp=0242401911&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0242401911&partnerID=8YFLogxK

    U2 - 10.1023/A:1026378916288

    DO - 10.1023/A:1026378916288

    M3 - Article

    AN - SCOPUS:0242401911

    VL - 55

    SP - 107

    EP - 122

    JO - International Journal of Computer Vision

    JF - International Journal of Computer Vision

    SN - 0920-5691

    IS - 2-3

    ER -