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

Image representation by complex cell responses.

Ingo J Wundrich1, Christoph von der Malsburg, Rolf P Würtz

  • 1Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780 Bochum, Germany. Ingo.Wundrich@neuroinformatik.ruhr-uni-bochum.de

Neural Computation
|November 2, 2004
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

The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns.

Neural computation·2026
Same author

How are segmentation and binding computed and represented in the brain?

Cognitive processing·2024
Same author

Toward understanding the neural code of the brain.

Biological cybernetics·2021
Same author

Computer Vision Technology in the Differential Diagnosis of Cushing's Syndrome.

Experimental and clinical endocrinology & diabetes : official journal, German Society of Endocrinology [and] German Diabetes Association·2019
Same author

An applet for the Gabor similarity scaling of the differences between complex stimuli.

Attention, perception & psychophysics·2016
Same author

Self-organization of control circuits for invariant fiber projections.

Neural computation·2015
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Image representation using Gabor wavelet transform magnitudes offers robustness to shifts, mimicking visual cortex complex cells. Reconstruction from these magnitudes is unique for band-limited, zero-mean images, aiding image understanding.

Area of Science:

  • Computational neuroscience
  • Image processing
  • Signal analysis

Background:

  • Complex cells in the visual cortex are modeled by Gabor wavelets.
  • Image representation insensitive to local shifts is crucial for image understanding.

Purpose of the Study:

  • To analyze image representation using the magnitudes of complex-valued Gabor wavelet transforms.
  • To investigate the technical usefulness of this representation for image understanding.
  • To determine the uniqueness of image reconstruction from Gabor wavelet transform magnitudes.

Main Methods:

  • Utilizing complex-valued Gabor wavelets for image transformation.
  • Analyzing the magnitudes of the resulting wavelet transform.
  • Investigating conditions for unique image reconstruction.

Related Experiment Videos

Main Results:

  • The Gabor wavelet transform magnitude representation is insensitive to small local shifts.
  • For band-limited images with zero mean, reconstruction from magnitudes is unique up to a sign for almost all images.

Conclusions:

  • This representation provides a biologically plausible model for early visual processing.
  • The shift-insensitivity and unique reconstruction properties enhance its utility in image understanding applications.