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

Invariant pattern recognition based on centroids.

S Chang1, H H Arsenault, P Garcia-Martinez

  • 1Optics Group, Institute for National Measurement Standards, National Research Council Canada, Building M-36, Ottawa, Ontario K1A OR6, Canada. shoude.chang@nrc.ca

Applied Optics
|March 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

Predictive model of variables associated with health-related quality of life in patients with advanced chronic kidney disease receiving hemodialysis.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2020
Same author

Multiple Epidermolytic Acanthomas on the Scrotum: What Genital Pruritus Can Reveal.

Actas dermo-sifiliograficas·2017
Same author

Progressive limitation of mouth opening.

Actas dermo-sifiliograficas·2016
Same author

Allergic reactions to meglumine antimoniate while treating cutaneous leishmaniasis.

Journal of the European Academy of Dermatology and Venereology : JEADV·2016
Same author

In vivo reflectance confocal microscopy characterization of silver deposits in localized cutaneous argyria.

The British journal of dermatology·2016
Same author

Optimum rotation-invariant filter for disjoint-noise scenes.

Applied optics·2010
Same journal

Multifunctional reconfigurable terahertz metasurface based on vanadium dioxide phase transition: achieving broadband absorption and efficient polarization conversion.

Applied optics·2026
Same journal

High-Q-factor electromagnetically induced transparency utilizing quasi-bound states in the continuum in an all-dielectric terahertz metasurface.

Applied optics·2026
Same journal

Automated stitching interferometry for high-precision metrology of X-ray mirrors.

Applied optics·2026
Same journal

Experimental demonstration of an approach to designing a metal-dielectric DBR resonant cavity structure.

Applied optics·2026
Same journal

High-precision wavefront reconstruction from a single-shot interferogram using a physics-driven hybrid feature calibration network.

Applied optics·2026
Same journal

Ultra-high-Q Fano resonance based on coupled topological corner states in Kagome photonic crystals.

Applied optics·2026
See all related articles

This study introduces a novel pattern recognition method using object centroids and conformal transforms. This approach achieves invariance to position, orientation, intensity, and scale for robust feature extraction.

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Traditional pattern recognition methods struggle with variations in object appearance.
  • Invariance to transformations like scale, rotation, and intensity is crucial for real-world applications.

Purpose of the Study:

  • To develop a novel pattern recognition method invariant to changes in position, orientation, intensity, and scale.
  • To leverage object centroids and conformal transformations for robust feature extraction.

Main Methods:

  • Utilizing object centroids as unique points related to energy distribution.
  • Applying conformal transforms to rearrange object energy distribution and generate multiple centroids.
  • Creating a feature vector based on these derived centroids for pattern recognition.

Related Experiment Videos

Main Results:

  • The proposed method generates a feature vector invariant to position, orientation, intensity, and scale.
  • Conformal transforms enable the creation of multiple unique centroids from a single object.
  • Demonstrated potential for effective pattern recognition and object registration.

Conclusions:

  • The new method offers a robust solution for pattern recognition challenges.
  • Invariant feature vectors derived from conformal transform-based centroids enhance object recognition accuracy.
  • This technique holds promise for various computer vision and image analysis tasks.