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

Neural network for three-dimensional object recognition based on digital holography.

Y Frauel, B Javidi

    Optics Letters
    |December 1, 2007
    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

    Resolution improvements in integral microscopy with Fourier plane recording.

    Optics express·2016
    Same author

    Free-depths reconstruction with synthetic impulse response in integral imaging.

    Optics express·2015
    Same author

    Digital holographic testing of biconvex lenses.

    Applied optics·2014
    Same author

    Random resampling masks: a non-Bayesian one-shot strategy for noise reduction in digital holography.

    Optics letters·2013
    Same author

    Multi-wavelengths digital holography: reconstruction, synthesis and display of holograms using adaptive transformation.

    Optics letters·2012
    Same author

    High-resolution far-field integral-imaging camera by double snapshot.

    Optics express·2012
    Same journal

    Gaussian-modulated continuous-variable quantum key distribution over 60 km fiber using an integrated silicon photonic receiver.

    Optics letters·2026
    Same journal

    E2E-OCT: end-to-end joint learning model using optical coherence tomography images for vocal cord leukoplakia diagnosis.

    Optics letters·2026
    Same journal

    Holographic generation of panoramic 3D scenes by concave ellipsoidal mirror reflection.

    Optics letters·2026
    Same journal

    Dual-pilot phase recovery with pair-wise maximum-ratio combining for coherent PONs.

    Optics letters·2026
    Same journal

    Mapping the whispering gallery modes of a CaF<sub>2</sub> disk resonator with half-tapered fibers to estimate the fundamental mode volume.

    Optics letters·2026
    Same journal

    Quantitative estimation of deep-subwavelength scale via dark-field scattering axial energy concentration decay profiles.

    Optics letters·2026
    See all related articles

    A novel two-layer neural network effectively processes three-dimensional (3D) images from digital holography. This system demonstrates robust 3D object detection, even with significant out-of-plane rotations.

    Area of Science:

    • Optics and Photonics
    • Computer Vision
    • Artificial Intelligence

    Background:

    • Digital holography enables the capture of three-dimensional (3D) image information.
    • Processing holographic 3D data presents challenges due to its complexity and potential distortions.
    • Developing automated methods for 3D object recognition is crucial for various applications.

    Purpose of the Study:

    • To introduce a two-layer neural network specifically designed for processing 3D images obtained via digital holography.
    • To train the network using a real 3D object to optimize its layer weights.
    • To evaluate the system's performance in detecting 3D objects under various distortions, including significant rotations.

    Main Methods:

    • Implementation of a two-layer neural network architecture.

    Related Experiment Videos

  • Training the network with a physical 3D object to determine optimal layer weights.
  • Conducting experimental validation to assess the system's detection and recognition capabilities.
  • Testing the system's resilience to distortions, specifically 360-degree out-of-plane rotations.

    • Main Results:

    • The trained neural network successfully processes three-dimensional (3D) holographic images.
    • Experimental results confirm the system's ability to detect 3D objects.
    • The system demonstrates robust performance in recognizing 3D objects despite various distortions.
    • Specifically, the system successfully recognized a 3D object with a 360-degree out-of-plane rotation.

    Conclusions:

    • The proposed two-layer neural network is an effective tool for processing 3D images from digital holography.
    • The system provides a reliable method for 3D object detection and recognition in the presence of distortions.
    • The demonstrated robustness to large rotations highlights the potential of this approach for real-world applications.