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

Radon transform orientation estimation for rotation invariant texture analysis.

Kourosh Jafari-Khouzani1, Hamid Soltanian-Zadeh

  • 1Radiology Image Analysis Lab, Henry Ford Health System, One Ford Place, 2F (Box 82), Detroit, MI 48202, USA. kjafari@rad.hfh.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 11, 2005
PubMed
Summary

This study introduces a novel rotation invariant texture classification method. By aligning textures to a principal direction using Radon transform, it significantly improves feature extraction and classification accuracy.

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

Reconstruction of MRI from undersampled k-spaces of double-contrast volume acquisitions using deep neural networks.

Magnetic resonance imaging·2026
Same author

Sex-related structural alterations across common epilepsies: a worldwide ENIGMA study.

bioRxiv : the preprint server for biology·2026
Same author

Editorial: Cognitive enhancement by brain stimulation techniques.

Frontiers in human neuroscience·2026
Same author

Abnormal functional connectivity patterns in temporal lobe epilepsy-An international ENIGMA-epilepsy study.

Epilepsia open·2026
Same author

Altered resting-state functional connectivity in delusional patients with schizophrenia or schizoaffective disorder: An fMRI study using threshold-free cluster-enhancement.

Psychiatry research. Neuroimaging·2026
Same author

fMRI features in recent suicide attempters performing the future imagination task.

Psychiatry research. Neuroimaging·2025

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Texture classification is crucial in image analysis.
  • Existing methods struggle with rotation invariance, especially for anisotropic textures.
  • Wavelet features are sensitive to rotation for directional textures.

Purpose of the Study:

  • To develop a rotation invariant texture classification method.
  • To address the challenge of feature variability due to image rotation.
  • To enhance the separation between different texture classes.

Main Methods:

  • Utilizing the Radon transform to detect the principal direction of textures.
  • Rotating textures to align their principal direction to 0 degrees.
  • Applying wavelet transform to extract rotation invariant features.

Related Experiment Videos

Main Results:

  • The proposed method achieves small intraclass variability.
  • Demonstrates good separation between different texture classes.
  • Outperforms existing texture classification methods in experiments.

Conclusions:

  • The novel approach effectively handles rotation invariance in texture classification.
  • Aligning textures based on principal direction significantly improves feature robustness.
  • The method shows superior performance on benchmark texture datasets.