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

Wavelet networks for face processing.

V Krüger1, G Sommer

  • 1Center for Automation Research, University of Maryland, College Park 20742, USA. vok@cfar.umd.edu

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|June 7, 2002
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

Childhood growth of singletons conceived following intracytoplasmic sperm injection - irrelevance of gonadotropin stimulation.

Frontiers in reproductive health·2024
Same author

Automated lung cancer assessment on 18F-PET/CT using Retina U-Net and anatomical region segmentation.

European radiology·2023
Same author

Towards microstructure-informed material models for human brain tissue.

Acta biomaterialia·2019
Same author

Viscoelastic parameter identification of human brain tissue.

Journal of the mechanical behavior of biomedical materials·2017
Same author

Rheological characterization of human brain tissue.

Acta biomaterialia·2017
Same author

Mechanical characterization of human brain tissue.

Acta biomaterialia·2016
Same journal

Multi-module collaborative optimization-driven fast speckle correlation imaging in variable environments.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Secrecy performance analysis of NOMA-UWOC systems over a vertically stratified WGG oceanic turbulence channel.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Backscattering of plane waves in a composite system containing a rough surface and anisotropic scatterers.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Aspherical surface construction methods based on extended Jacobi polynomials.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

OCT sidelobe suppression method based on dual-path phase sinusoidal modulation and minimum value fusion.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Optical design concepts using wavelength-selective diffractive optics to enable miniaturized multimodal endoscopic imaging across separated spectral ranges.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
See all related articles

Wavelet networks (WNs), combining RBF networks and wavelet transforms, offer efficient data reduction for image analysis. This study highlights their underappreciated potential for object representation, particularly in face tracking and recognition tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Image Processing

Background:

  • Wavelet networks (WNs) integrate radial basis function (RBF) networks with wavelet decomposition.
  • WNs have been largely overlooked since their introduction in 1992.
  • Their potential for efficient data representation remains underestimated.

Purpose of the Study:

  • To analyze the properties and advantages of WNs for object representation.
  • To demonstrate the effectiveness of WNs in face tracking applications.
  • To leverage WNs for efficient face recognition and pose estimation.

Main Methods:

  • Utilizing wavelet coefficients directly linked to image data via wavelet transform.
  • Optimizing wavelet parameters within WNs for direct function-wavelet relationships.

Related Experiment Videos

  • Applying the optimized filter bank principle inherent in WNs.

    • Main Results:

    • WNs achieve significant data reduction, enhancing algorithm efficiency.
    • Optimized wavelets derived from WNs serve as effective filter banks.
    • Experiments show successful application of WNs in face tracking, recognition, and pose estimation.

    Conclusions:

    • WNs offer substantial advantages for object representation due to inherent data reduction.
    • The optimized filter bank nature of WNs facilitates efficient image analysis tasks.
    • WNs present a promising, yet underutilized, tool for advanced computer vision applications.