Jove
Visualize
Contact Us

Related Experiment Videos

Visually distinct patterns with matching subband statistics.

Joshua Gluckman1

  • 1Department of Computer Science, Polytechnic University, Brooklyn, NY 11201, USA. jgluckma@poly.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|February 4, 2005
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 journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles
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

Statistical representations of visual patterns using filter responses can be similar even for visually distinct images. This study demonstrates how to create patterns with identical marginal and joint statistics, challenging their discriminative power in computer vision.

Area of Science:

  • Computer Vision
  • Image Processing
  • Statistical Pattern Recognition

Background:

  • Visual patterns are often represented by statistical distributions of filter responses (e.g., Gaussian, Laplacian, Gabor).
  • Marginal and joint distributions of these filter responses are widely used in tasks like texture classification, synthesis, object detection, and image retrieval.

Purpose of the Study:

  • To investigate the discriminative ability of statistical representations (marginal and joint distributions of filter responses) for visual stimuli.
  • To determine if patterns with identical statistical properties can be visually distinct.

Main Methods:

  • Derivation of patterns with provably identical marginal and joint statistical properties.
  • Demonstration of sufficient conditions for matching the first k moments of marginal distributions.

Related Experiment Videos

  • Matching marginal statistics of subband images formed by filter convolution.
  • Examination of joint statistics and generation of images with similar subband response distributions.
  • Derivation of distinct periodic patterns with approximately equivalent subband statistics for arbitrary filter sets.

    • Main Results:

    • Successfully derived visual patterns that share identical marginal and joint statistical properties but are visually distinct.
    • Established methods to match marginal statistics of subband images for a given filter set.
    • Demonstrated the existence of distinct periodic patterns with similar subband statistics across various filter sets.

    Conclusions:

    • The study highlights limitations in using solely marginal and joint statistical distributions of filter responses for robust visual discrimination.
    • Identical statistical properties do not guarantee visual similarity, indicating the need for more sophisticated pattern representations in computer vision.