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

Computer vision and natural constraints.

C M Brown

    Science (New York, N.Y.)
    |June 22, 1984
    PubMed
    Summary
    This summary is machine-generated.

    Computer vision, the automatic construction of scene descriptions from images, is advancing. Research focuses on extracting physical scene properties and transforming image data into symbolic descriptions for AI.

    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

    Compartment-guided assembly of large-scale molecular models with Bentopy.

    Protein science : a publication of the Protein Society·2026
    Same author

    Public reporting guidelines for outbreak data: Enabling accountability for effective outbreak response by developing standards for transparency and uniformity.

    Public health·2025
    Same author

    Photosymbiosis reduces the environmental stress response under a heat challenge in a facultatively symbiotic coral.

    Scientific reports·2024
    Same author

    Néel ordering in the distorted honeycomb pyrosilicate: C-Er<sub>2</sub>Si<sub>2</sub>O<sub>7</sub>.

    Journal of physics. Condensed matter : an Institute of Physics journal·2020
    Same author

    Common acoustic phonon lifetimes in inorganic and hybrid lead halide perovskites.

    Physical review materials·2020
    Same author

    Variations in competencies needed to complete surgical training.

    BJS open·2019
    Same journal

    Erratum for the Research Article "Detecting supramolecular organic nanoparticles during heat wave".

    Science (New York, N.Y.)·2026
    Same journal

    Local signals, systemic decline.

    Science (New York, N.Y.)·2026
    Same journal

    The mechanics of liver regeneration.

    Science (New York, N.Y.)·2026
    Same journal

    Computing in a memory with physics.

    Science (New York, N.Y.)·2026
    Same journal

    Retraction.

    Science (New York, N.Y.)·2026
    Same journal

    Making time.

    Science (New York, N.Y.)·2026
    See all related articles

    Area of Science:

    • Computer Vision
    • Artificial Intelligence

    Background:

    • Computer vision, focused on automatic scene description from images, is a rapidly evolving field.
    • Approaches vary in their integration of symbolic, domain-specific knowledge and inference.

    Purpose of the Study:

    • To explore current research in computer vision, particularly methods for extracting physical scene properties.
    • To understand the hierarchy of operations transforming image data into symbolic descriptions.

    Main Methods:

    • Focus on extracting physical scene properties like depth, surface orientation, and reflectance.
    • Utilizing general assumptions about the scene domain for parameter extraction.
    • Examining processes such as stereo fusion and image partitioning.

    Main Results:

    Related Experiment Videos

    • Current research emphasizes extracting physical scene parameters with minimal domain-specific knowledge.
    • Physical parameter extraction is a key step in a larger process of symbolic description generation.
    • Stereo fusion and image partitioning are illustrative examples of these processes.

    Conclusions:

    • Computer vision research significantly impacts theories of animal perception.
    • Advances in computer vision are informing the design of AI computing architectures.