Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Flexible skew-symmetric shape model for shape representation, classification, and sampling.

Sajjad H Baloch1, Hamid Krim

  • 1Department of Electrical and Computer Engineering, North Carolina State University, Raleigh 27695-7914, USA. shbaloch@ncsu.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 3, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Analysis Dictionary Learning Based Classification: Structure for Robustness.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same author

Deep Dictionary Learning: A PARametric NETwork Approach.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same author

Metric Driven Classification: A Non-Parametric Approach Based on the Henze-Penrose Test Statistic.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018
Same author

Subspace learning of dynamics on a shape manifold: a generative modeling approach.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2014
Same author

Human activity as a manifold valued random process.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2012
Same author

Multiphase joint segmentation-registration and object tracking for layered images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2010

This study introduces a flexible skew-symmetric shape model (FSSM) to address skewness in shape data, improving statistical shape modeling for applications like medical imaging. The FSSM accounts for non-Gaussian data, enabling accurate mean shape learning, classification, and generation of new shapes.

Area of Science:

  • Computational geometry
  • Statistical modeling
  • Medical image analysis

Background:

  • Skewness in shape data is common in applications like medical imaging but often ignored in statistical shape models.
  • A Gaussian assumption for shape data is frequently unrealistic, necessitating models that account for skewness.

Purpose of the Study:

  • To present a novel statistical method, the flexible skew-symmetric shape model (FSSM), for shape modeling that accommodates data skewness.
  • To develop a general shape model capable of learning a mean shape, classifying shapes, and generating new shape realizations.

Main Methods:

  • The FSSM is derived from an extended class of flexible skew-symmetric distributions to ensure robustness to skewness.
  • Shapes are modeled as realizations of a spatial random process, learning a shape distribution that captures variability around a mean.

Related Experiment Videos

  • The FSSM is formulated as a joint bimodal distribution of angle and distance from the centroid for shape realizations.

    • Main Results:

    • The FSSM successfully accommodates departures from Gaussianity in shape data.
    • The model enables the extraction of principal curves from point clouds.
    • Mean shapes are recovered from the distribution's modes, and classification is performed using maximum likelihood estimation.

    Conclusions:

    • The flexible skew-symmetric shape model (FSSM) provides a robust and general approach to statistical shape modeling, particularly for skewed data.
    • FSSM enhances shape analysis by enabling accurate mean shape representation, classification, and generation of novel shapes.
    • This method advances shape modeling by incorporating skewness and allowing for principal curve extraction.