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

Early processing of visual information.

D Marr

    Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences
    |October 19, 1976
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a theory for early visual processing, detailing how images are first described by a "primal sketch" and then grouped for recognition. This approach emphasizes bottom-up processing for efficient figure-ground separation before higher-level interpretation.

    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

    Infliximab vs. adalimumab in Crohn's disease: results from 327 patients in an Australian and New Zealand observational cohort study.

    Alimentary pharmacology & therapeutics·2016
    Same author

    Representation and recognition of the movements of shapes.

    Proceedings of the Royal Society of London. Series B, Biological sciences·1982
    Same author

    Directional selectivity and its use in early visual processing.

    Proceedings of the Royal Society of London. Series B, Biological sciences·1981
    Same author

    Visual information processing: the structure and creation of visual representations.

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·1980
    Same author

    Smallest channel in early human vision.

    Journal of the Optical Society of America·1980
    Same author

    Theory of edge detection.

    Proceedings of the Royal Society of London. Series B, Biological sciences·1980
    Same journal

    The microlandscapes of tree trunks: the effect of lichen and tree-level characteristics on arthropod communities.

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
    Same journal

    Centimetre-scale landscapes to assess the motion behaviour and cognition of gastropods and bivalves.

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
    Same journal

    Intertidal microcosms of wave-swept rocky shores: ecological and physiological insights from a uniquely stressful environment.

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
    Same journal

    Temporal and spatial variation in temperature and oxygen at the microscale: key niche axes for aquatic life.

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
    Same journal

    Natural microcosms in ecology: fulfilling the promise of model systems?

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
    Same journal

    Microbe-induced galls and plant defence: metabolite crosstalk in a co-evolutionary battle.

    Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
    See all related articles

    Area of Science:

    • Computer Vision
    • Image Processing
    • Computational Neuroscience

    Background:

    • Early visual information processing theories often struggle with efficient image analysis.
    • Existing machine vision programs may rely too heavily on top-down information.
    • The need for robust methods to extract and group image features is critical.

    Purpose of the Study:

    • To introduce and implement a theory for early visual information processing.
    • To describe a two-step process: creating a primal sketch and grouping its elements.
    • To propose a model where figure-ground separation precedes detailed shape description.

    Main Methods:

    • Computing a 'primal sketch' representing grey-level changes (edges, lines, blobs) with parameters like position and orientation.

    Related Experiment Videos

  • Employing grouping mechanisms based on symbolic processes and first-order discriminations on primal sketch elements.
  • Utilizing techniques for figure-ground separation that are largely independent of image content.

    • Main Results:

    • Demonstration of images at various stages of analysis using the implemented theory.
    • The primal sketch provides a rich, primitive description of image intensity changes.
    • Grouping operations and first-order discriminations effectively implement 'non-attentive' vision.

    Conclusions:

    • Figure-ground separation can be achieved early in processing, independent of specific image details.
    • This model relegates the use of top-down, high-level knowledge to later stages.
    • The proposed approach offers a more efficient and robust framework for machine vision.