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

Segmenting textures using cells with adaptive receptive fields

E Meśrobian1, J Skrzypek

  • 1Computer Science Department, University of California, Los Angeles 90024, USA.

Spatial Vision
|January 1, 1995
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

Azoospermia in a renal transplant recipient during sirolimus (rapamycin) treatment.

Andrologia·2007
Same author

Cellular and biochemical markers in semen indicating male accessory gland inflammation.

Andrologia·2003
Same author

Treatment with levofloxacin does not resolve asymptomatic leucocytospermia--a randomized controlled study.

Andrologia·2003
Same author

Levels of interleukin-6 and interleukin-8 in seminal fluid of men attending an andrological clinic.

Andrologia·2003
Same author

Influence of antisperm antibodies on the acrosome reaction as determined by flow cytometry.

Fertility and sterility·2001
Same author

[TSH-receptor antibodies in thyroid diseases].

Polskie Archiwum Medycyny Wewnetrznej·1997

This study introduces a novel neural network for textural segmentation, using adaptive receptive fields to identify boundaries. The model mimics early visual processes for preattentive texture segregation.

Area of Science:

  • Neuroscience
  • Computer Vision
  • Computational Neuroscience

Background:

  • Textural segmentation is crucial for figure-ground discrimination in visual processing.
  • Existing models do not adequately account for adaptive boundary delimitation in textured regions.
  • Orientation contrast significantly influences texture pattern segregation.

Purpose of the Study:

  • To present a novel neural network architecture for adaptive textural segmentation.
  • To model how early visual areas process texture segregation.
  • To investigate the role of context-dependent cell responses in visual segmentation.

Main Methods:

  • Developed a neural network with adaptive receptive fields.
  • Employed diffusive interpolation of feature orientation estimates.

Related Experiment Videos

  • Detected boundaries at orientation contrast gradients.

    • Main Results:

    • The model adaptively delimits uniformly textured regions.
    • Orientation contrast gradients are effectively used for segmentation.
    • The model's performance aligns with neurophysiological data from early visual areas (V1, V2, V3/V5).

    Conclusions:

    • Early visual processes can perform preattentive textural segregation.
    • Textural segmentation is a dynamic process involving context-dependent cell responses.
    • Adaptive receptive fields provide a viable mechanism for textural segmentation.