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

Symbolic signatures for deformable shapes.

Salvador Ruiz-Correa1, Linda G Shapiro, Marina Meila

  • 1Department of Radiology, University of Washington and Children's Hospital and Regional Medical Center, 4800 Sand Point Way NW R-5438, Seattle, WA 98105, USA. sruiz@u.washington.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 13, 2006
PubMed
Summary

This study introduces a new framework for recognizing deformable object classes from 3D range data. The symbolic-signature representation enables robust shape recognition, advancing computer vision capabilities.

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

[Diagnosis of congenital heart disease using Deep Learning in pediatric chest X-rays: A proof of concept].

Revista medica del Instituto Mexicano del Seguro Social·2026
Same author

A three-dimensional multi-modal foundation model for optical coherence tomography.

Nature biomedical engineering·2026
Same author

Interactive visualization of metric distortion in nonlinear data embeddings using the distortions package.

Briefings in bioinformatics·2026
Same author

Global patterns and predictors of initial treatment in early rheumatoid arthritis: insights from a multinational machine learning study.

Clinical rheumatology·2026
Same author

Lateral mandibular ridge: A unique feature of the auriculocondylar syndrome.

European journal of radiology·2025
Same author

Revisiting a Rare Anomaly Described 25 Years Ago in the <i>AJNR</i>: A Journey from Pediatric Hemifacial Microsomia and Middle Cranial Fossa Aplasia to CSF-Lymphatic Fistula and Spontaneous Intracranial Hypotension as an Adult.

AJNR. American journal of neuroradiology·2025

Area of Science:

  • Computer Vision
  • Machine Learning
  • 3D Shape Recognition

Background:

  • Recognizing object classes from shape is a significant challenge in computer vision.
  • Variability in object shapes and partial data from sensors complicate recognition tasks.
  • Existing methods often struggle with deformable objects and require specific shape data.

Purpose of the Study:

  • To develop an algorithmic framework for recognizing classes of deformable shapes from range data.
  • To introduce a novel symbolic-signature representation for robust shape generalization.
  • To create a system capable of classifying diverse object shape classes.

Main Methods:

  • Utilized a component-based approach to generalize surface representations.
  • Introduced a symbolic-signature representation robust to deformations.

Related Experiment Videos

  • Developed a system for recognizing and classifying object shape classes from range data.

    • Main Results:

    • Demonstrated a system capable of recognizing and classifying various object shape classes.
    • The symbolic-signature representation proved effective for deformable shapes.
    • Successfully applied the framework in large-scale experiments.

    Conclusions:

    • The developed framework effectively recognizes deformable object classes from range data.
    • The symbolic-signature representation offers a robust alternative to numeric representations for shape analysis.
    • The system has potential applications in scene analysis and medical diagnosis.