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

Adaptive, optical, radial basis function neural network for handwritten digit recognition.

W E Foor, M A Neifeld

    Applied Optics
    |November 10, 2010
    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

    Optical memory: introduction by the feature editors.

    Applied optics·2010
    Same author

    Optical design for page access to volume optical media.

    Applied optics·2010
    Same author

    Error-correction schemes for volume optical memories.

    Applied optics·2010
    Same author

    Optical dual-scale architecture for neural image recognition.

    Applied optics·2010
    Same author

    Lens-design issues affecting parallel readout of optical disks.

    Applied optics·2010
    Same author

    Improvements in the capacity of computer-generated holographic storage using the Lee method with sparse multivalued reconstructions.

    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

    An adaptive optical classifier for handwritten digit recognition significantly improves accuracy. This system uses on-line learning to achieve 92.7% correct recognition, outperforming non-adaptive methods.

    Area of Science:

    • Computer Vision
    • Optical Computing
    • Machine Learning

    Background:

    • Handwritten digit recognition is a challenging task in pattern recognition.
    • Existing optical classifiers often lack robustness to system imperfections and noise.
    • Adaptive learning mechanisms can enhance classifier performance and reliability.

    Purpose of the Study:

    • To experimentally demonstrate an adaptive, optical radial basis function classifier for handwritten digit recognition.
    • To investigate the system's robustness to optical imperfections and noise through on-line adaptation.
    • To compare the performance of adaptive versus non-adaptive training methods.

    Main Methods:

    • Development of a spatially multiplexed optical system for Euclidean distance computation.

    Related Experiment Videos

  • Implementation of on-line adaptation of weights and basis function widths using software emulation of an electronic chip.
  • Utilizing dual vector-matrix multipliers and a contrast-reversing spatial light modulator for parallel processing.
  • Comparison of experimental results with a detailed computer model to analyze noise influences.

    • Main Results:

    • Achieved an experimental recognition rate of 92.7% correct out of 300 testing samples with adaptive training.
    • Non-adaptive training yielded a significantly lower correct recognition rate of 31.0%.
    • The adaptive system demonstrated robustness to optical system imperfections and noise.

    Conclusions:

    • The adaptive optical radial basis function classifier offers a substantial improvement in handwritten digit recognition accuracy.
    • On-line adaptation is crucial for enhancing the robustness and performance of optical pattern recognition systems.
    • The study provides insights into noise sources affecting optical system performance through comparative analysis with a computer model.