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

Computational vision and regularization theory.

T Poggio, V Torre, C Koch

    Nature
    |September 2, 1985
    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

    Iatrogenic adrenal insufficiency as a side-effect of combined treatment of itraconazole and budesonide.

    The European respiratory journal·2002
    Same author

    Itraconazole treatment of allergic bronchopulmonary aspergillosis in patients with cystic fibrosis.

    Allergy·2002
    Same author

    Microbial load of drinking water reservoir tributaries during extreme rainfall and runoff.

    Applied and environmental microbiology·2002
    Same author

    Sulphation of the salivary mucin MG1 (MUC-5B) is not correlated to the degree of its sialylation and is unaffected by cystic fibrosis.

    Pflugers Archiv : European journal of physiology·2002
    Same author

    Altered sialyl- and fucosyl-linkage on mucins in cystic fibrosis patients promotes formation of the sialyl-Lewis X determinant on salivary MUC-5B and MUC-7.

    Pflugers Archiv : European journal of physiology·2002
    Same author

    Soil surface structure effect on isoproturon and diflufenican loss in runoff.

    Journal of environmental quality·2002
    Same journal

    Six ways to put the public at the heart of science and policy.

    Nature·2026
    Same journal

    The complex truth about trust in science.

    Nature·2026
    Same journal

    Have people stopped trusting science? The data tell a surprising story.

    Nature·2026
    Same journal

    How FAIR data are helping to build trust in science.

    Nature·2026
    Same journal

    Scientists should recognize their own political biases to build public trust.

    Nature·2026
    Same journal

    Harmonizing standards and resources for the medical genome.

    Nature·2026
    See all related articles

    Computational vision recovers surface properties from image data using regularization methods to solve ill-posed problems. These methods yield algorithms and circuits mimicking neural processes for visual perception.

    Area of Science:

    • Computer Vision
    • Neuroscience
    • Image Processing

    Background:

    • Recovering physical properties like surface distance and edges from visual data is crucial for understanding the environment.
    • Image data is inherently ambiguous and noisy, posing significant challenges for computational systems.
    • Early vision is increasingly viewed as a collection of ill-posed problems.

    Purpose of the Study:

    • To explore how computational vision can derive surface property descriptions from ambiguous image data.
    • To investigate the application of regularization methods for solving ill-posed problems in early vision.
    • To explore potential neural equivalents of computational vision algorithms.

    Main Methods:

    • Utilizing regularization methods to address ill-posed problems in image data analysis.

    Related Experiment Videos

  • Developing algorithms based on regularization for visual property recovery.
  • Designing parallel analog circuits inspired by computational vision approaches.

    • Main Results:

    • Demonstrated that regularization methods can effectively solve ill-posed problems in visual data.
    • Developed algorithms and circuits capable of recovering physical surface properties.
    • Identified computational approaches suggestive of neural mechanisms in the brain.

    Conclusions:

    • Regularization methods provide a robust framework for computational vision tasks involving ambiguous data.
    • The developed algorithms and circuits offer insights into how the brain might process visual information.
    • This research bridges computational approaches with potential neural underpinnings of vision.