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

Implementation of a polychromatic Hamming net for color image classification.

C M Uang, F T Yu, K T Kim

    Applied Optics
    |October 12, 2010
    PubMed
    Summary

    This study introduces a novel color image classifier using a polychromatic Hamming network. Simplified algorithms enhance efficiency for color image recognition tasks.

    Related Concept Videos

    Color Vision01:24

    Color Vision

    Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
    Classification of Systems-I01:26

    Classification of Systems-I

    Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
    Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

    You might also read

    Related Articles

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

    Sort by
    Same author

    Temporal characterization of a two-color laser field using tunneling ionization.

    Optics express·2022
    Same author

    High-detectivity perovskite-based photodetector using a Zr-doped TiO <sub></sub> cathode interlayer.

    RSC advances·2022
    Same author

    Extraordinary Strengthening Effect of Carbon Nanotubes in Metal-Matrix Nanocomposites Processed by Molecular-Level Mixing.

    Advanced materials (Deerfield Beach, Fla.)·2021
    Same author

    Test of Lepton-Flavor Universality in B→K^{*}ℓ^{+}ℓ^{-} Decays at Belle.

    Physical review letters·2021
    Same author

    Measurement of R(D) and R(D^{*}) with a Semileptonic Tagging Method.

    Physical review letters·2020
    Same author

    Observation of the Radiative Decays of ϒ(1S) to χ_{c1}.

    Physical review letters·2020

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Traditional image classification methods often struggle with the complexity of color information.
    • Hamming networks offer a robust framework for pattern recognition but require adaptation for color data.

    Purpose of the Study:

    • To develop and evaluate a color exemplar-based Hamming network for enhanced color image classification.
    • To optimize the network's performance by simplifying its core algorithms.

    Main Methods:

    • Construction of a polychromatic Hamming layer and winner-take-all (WTA) layer interconnection weight matrix (IWM) using color decomposition and composition.
    • Simplification of the WTA algorithm to minimize computational cycles.
    • Simulation and experimental validation of the proposed color Hamming network.

    Main Results:

    • Demonstration of the color Hamming network's functionality through simulations.
    • Experimental validation confirming the effectiveness of the proposed approach for color image classification.
    • Evidence of reduced iteration cycles in the simplified WTA layer.

    Conclusions:

    • The proposed color exemplar-based Hamming network provides an effective solution for color image classification.
    • Algorithm simplification leads to improved computational efficiency.
    • The method shows promise for real-world applications in color image recognition.

    Related Experiment Videos