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

Geometry-invariant texture retrieval using a dual-output pulse-coupled neural network.

Xiaojun Li1, Yide Ma, Zhaobin Wang

  • 1School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu Province 730000, China. xjlilzu@hotmail.com

Neural Computation
|August 20, 2011
PubMed
Summary

A new dual-output pulse coupled neural network (DPCNN) model offers stable texture descriptions resistant to geometric transformations. This DPCNN model achieves superior geometry-invariant texture retrieval compared to existing methods.

Related Concept Videos

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)01:15

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT) is an advanced Nuclear Magnetic Resonance (NMR) technique specifically designed to detect and enhance the signals of low-abundance nuclei, such as carbon-13 and nitrogen-15, in small molecules. The fundamental principle behind INEPT is the transfer of polarization from a more abundant and highly polarizable nucleus, typically hydrogen-1, to the low-abundance nucleus of interest. This process effectively boosts the NMR signal of the...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cassiaside C alleviates IRI-induced AKI through restoring the expression of ATGL to reduce lipid droplet accumulation.

Biochemical and biophysical research communications·2026
Same author

The role of transposable elements activity in genomic instability and their relationship to aging process.

Cell cycle (Georgetown, Tex.)·2026
Same author

Self-Assembling P38 Peptide Inhibitor Nanoparticles Ameliorate the Transition from Acute to Chronic Kidney Disease by Suppressing Ferroptosis.

Advanced healthcare materials·2024
Same author

Effects of umami substances as taste enhancers on salt reduction in meat products: A review.

Food research international (Ottawa, Ont.)·2024
Same author

Introducing hafnium to atomically small- and medium-sized tin clusters (HfSn<sub>n</sub><sup>0/-/2-</sup> (n = 4-17)): A computational investigation of geometrical and growth behavior, spectral properties, electronic configuration and thermochemistry.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2024
Same author

Developing active and intelligent biodegradable packaging from food waste and byproducts: A review of sources, properties, film production methods, and their application in food preservation.

Comprehensive reviews in food science and food safety·2024

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Processing

Background:

  • Geometric transformations (translation, rotation, scale, distortion) significantly challenge texture description accuracy.
  • Existing texture retrieval models often struggle with maintaining descriptive stability under such transformations.

Purpose of the Study:

  • To introduce a novel dual-output pulse coupled neural network (DPCNN) model.
  • To enhance the stability and invariance of texture descriptions against geometric transformations.
  • To improve geometry-invariant texture retrieval performance.

Main Methods:

  • A novel dual-output pulse coupled neural network (DPCNN) model was developed.
  • Time series derived from DPCNN's binary image outputs were used as texture features.

Related Experiment Videos

  • Features were tested for invariance to translation, rotation, scale, and distortion.
  • Performance was evaluated against existing models using Brodatz and VisTex databases.

    • Main Results:

    • The proposed DPCNN model demonstrated superior performance in geometry-invariant texture retrieval.
    • Experimental results confirmed the model's effectiveness across various transformations and datasets.
    • DPCNN showed robustness when tested with noisy image data.

    Conclusions:

    • The DPCNN model provides a stable and robust approach to texture description.
    • It significantly outperforms existing methods for geometry-invariant texture retrieval.
    • The model's invariance and robustness make it suitable for real-world image analysis applications.