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 Video

Updated: Jul 19, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

A Hopfield neural network for image change detection.

Gonzalo Pajares1

  • 1Departamento de Sistemas Informáticos y Programación, Facultad de Informática, Universidad Complutense, Madrid 28040, Spain. pajares@dacya.ucm.es

IEEE Transactions on Neural Networks
|September 28, 2006
PubMed
Summary

This study introduces an analog Hopfield neural network (HNN) for automatic image change detection, providing change strength beyond simple binary labels. This novel approach optimizes pixel analysis by balancing neighborhood and individual pixel information.

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

Filter pruning for convolutional neural networks in semantic image segmentation.

Neural networks : the official journal of the International Neural Network Society·2023
Same author

Artificial Intelligence Techniques for Automatic Detection of Peri-implant Marginal Bone Remodeling in Intraoral Radiographs.

Journal of digital imaging·2023
Same author

Automatic computation of mandibular indices in dental panoramic radiographs for early osteoporosis detection.

Artificial intelligence in medicine·2020
Same author

Structural correlates of apathy in Alzheimer's disease: a multimodal MRI study.

International journal of geriatric psychiatry·2016
Same author

Sensors and technologies in Spain: state-of-the-art.

Sensors (Basel, Switzerland)·2014
Same author

New trends in robotics for agriculture: integration and assessment of a real fleet of robots.

TheScientificWorldJournal·2014

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Traditional image change detection often assigns binary labels (changed/unchanged) to pixels.
  • Existing methods may ignore a pixel's own information, relying solely on neighbor data.
  • This can lead to suboptimal change detection accuracy.

Purpose of the Study:

  • To present an optimization relaxation approach using an analog Hopfield neural network (HNN) for image change detection.
  • To develop an automatic image change detection method that quantifies the strength of change.
  • To overcome limitations of existing methods by incorporating both neighborhood and individual pixel information.

Main Methods:

  • A difference image is generated by pixel-wise subtraction of two input images.

Related Experiment Videos

Last Updated: Jul 19, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • A network topology maps each pixel in the difference image to a node in the HNN.
  • An energy function is derived to guide the network towards stable states, allowing analog node values.

    • Main Results:

    • The analog HNN approach enables the determination of change strength, not just binary classification.
    • The model effectively balances the influence of a pixel's neighborhood with its own characteristics.
    • Performance is validated through comparative analysis with existing image change detection techniques.

    Conclusions:

    • The proposed analog Hopfield neural network offers an advanced method for automatic image change detection.
    • This approach provides richer information by quantifying change strength and considering individual pixel data.
    • The HNN customization enhances accuracy and robustness in image change detection tasks.