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

[Identification of neuronal system objects with standards].

S R Gutman

    Biofizika
    |March 1, 1976
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel neural network system capable of identifying 3D objects by their characteristic points, regardless of object transformations or partial occlusion. This allows for simultaneous identification of multiple objects within the system's presented standards.

    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

    [Biomechanical and neurophysiological characteristics of voluntary rhythmic movements in humans].

    Biofizika·1996
    Same author

    Abnormal motor patterns in the framework of the equilibrium-point hypothesis: a cause for dystonic movements?

    Biological cybernetics·1994
    Same author

    Kinematic description of variability of fast movements: analytical and experimental approaches.

    Biological cybernetics·1993
    Same author

    Basic functions of variability of simple pre-planned movements.

    Biological cybernetics·1992
    Same author

    Relativistic effects in single-joint voluntary movements.

    Biological cybernetics·1991
    Same author

    [Amplitude modulation of an electroencephalogram, connected with initiation and cessation of movement].

    Biofizika·1990
    Same journal

    [On Atomic Nuclear Fusion Processes at Low-Temperatures. An Enhancement of the Probability of Transition through a Potential Barrier Due to the So-Called Barrier Anti-Zeno Effect].

    Biofizika·2016
    Same journal

    [An Iterative Continuous-Event Model of the Population Outbreak of Phytophagous Hemiptera].

    Biofizika·2016
    Same journal

    [Providing the Optimal Insolation of a Photobiological Architectural Shell for Microalgae Cultivation].

    Biofizika·2016
    Same journal

    [Neurodynamic Bases of Imitation Learning and Episodic Memory].

    Biofizika·2016
    Same journal

    [Some Approaches to Activation of Antitumor Resistance Mechanisms and Functional Analogs in Categories of Synergetics].

    Biofizika·2016
    Same journal

    [Mechanism of Formation of Cardiac Arrhythmia Due to Pathological Distribution of Myocardium Conductivity].

    Biofizika·2016
    See all related articles

    Area of Science:

    • Computer Vision
    • Neuroscience
    • Artificial Intelligence

    Context:

    • Object recognition challenges in computer vision.
    • The role of neural networks in visual processing.
    • Developing robust object identification systems.

    Purpose:

    • To propose a neural network system for 3D object identification.
    • To demonstrate object identification invariant to transformations and occlusion.
    • To enable simultaneous recognition of multiple objects.

    Summary:

    • A neural network system is presented for identifying 3D objects based on characteristic point coordinates, termed the 'standard'.
    • The system achieves identification independent of object shifts, rotations, scaling, and partial shielding.

    Related Experiment Videos

  • It comprises feedback nets for optimal transformations, proximity calculation, and hypothesis generation for characteristic point correspondence.

    • Impact:

    • Enables robust and efficient 3D object recognition in complex visual scenes.
    • Potential applications in robotics, autonomous systems, and augmented reality.
    • Advances the understanding of neural mechanisms for visual invariance.