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

Metamorphs: deformable shape and appearance models.

Xiaolei Huang1, Dimitris N Metaxas

  • 1Computer Science and Engineering Department, Lehigh University, Berthlehem, PA 18015, USA. huang@cse.lehigh.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 21, 2008
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

Tephritid26: A standardized, multi-angle image dataset of quarantine-significant true fruit flies for deep learning-based identification.

Scientific data·2026
Same author

Caste polymorphism and distribution of sensilla in the social aphid Pseudoregma bambucicola (Takahashi, 1921).

Arthropod structure & development·2026
Same author

Real-time prediction of trauma-induced coagulopathy using an inverted transformer (trauma-former): a methodological feasibility and simulation study based on the ADEMP framework.

BMC medical research methodology·2026
Same author

Structural insights into histone mimicry by the small hepatitis delta antigen.

The Journal of biological chemistry·2026
Same author

Olfactory Responses of <i>Apis mellifera</i> and <i>Bombus terrestris</i> to Floral Volatiles from Three Solanaceae Crops.

Insects·2026
Same author

Transcriptome-Metabolome Integration Deciphers the Metabolic and Transcriptional Reprogramming in Mice Due to <i>Vespa mandarinia</i> Venom.

Toxins·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces novel deformable models that unify shape and appearance within a single space. These models, represented by distance maps, simultaneously deform both boundary and interior using Free Form Deformations.

Area of Science:

  • Computer Vision
  • Medical Imaging
  • Geometric Modeling

Background:

  • Traditional deformable models focus on shape (active contours) or appearance separately.
  • Integrating shape and appearance in a unified framework remains a challenge.

Purpose of the Study:

  • To present a new deformable modeling strategy that unifies shape and appearance.
  • To represent models implicitly using distance transforms for integrated deformation.

Main Methods:

  • Proposed deformable models are conceptualized as deforming disks or volumes.
  • Model shape is embedded in a higher dimensional space via distance transforms (distance map images).
  • Free Form Deformations (FFD) are employed for simultaneous warping of the volumetric space, deforming both boundary and interior.

Related Experiment Videos

Main Results:

  • The new models define both shape and appearance in the pixel space.
  • Simultaneous deformation of shape and appearance is achieved through FFD.

Conclusions:

  • The proposed unified space for deformable models enhances integration of shape and appearance.
  • Distance map representation and FFD offer a robust method for simultaneous deformation.