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

Implementation of parallel thinning algorithms using recurrent neural networks.

R Krishnapuram1, L F Chen

  • 1Dept. of Electr. and Comput. Eng., Missouri Univ., Columbia, MO.

IEEE Transactions on Neural Networks
|January 1, 1993
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

[Development and validation of an extremely-low frequency pressure reactivity index for traumatic brain injury outcomes].

Zhonghua nei ke za zhi·2026
Same author

Precise Measurement of the Cosmic Ray Helium Spectrum above 0.1 PeV.

Physical review letters·2026
Same author

[Use of modified balloon pulmonary angioplasty in the treatment of chronic thromboembolic pulmonary hypertension: a retrospective study from a single center].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2026
Same author

[Analysis of genetic association between exon polymorphisms of <i>ADH4</i> and <i>ADH7</i> and risky drinking behavior of alcoholic liver disease].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2024
Same author

[Wilson's disease misdiagnosed as autoimmune hepatitis: a case report and literature review].

Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology·2024
Same author

[Application value of folate receptor-positive circulating tumor cells in the diagnosis of head and neck squamous cell carcinoma].

Zhonghua yi xue za zhi·2024
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Recurrent neural networks effectively perform skeletonization and thinning on binary images by learning pixel deletion rules. A modified Wang-Zhang algorithm yields more visually appealing skeletons.

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Skeletonization and thinning are crucial image processing techniques for reducing shapes to their essential structure.
  • Traditional algorithms can be complex and may not always produce optimal results.

Purpose of the Study:

  • To investigate the application of recurrent neural networks (RNNs) for image skeletonization and thinning.
  • To develop and present RNN architectures capable of implementing established thinning algorithms.
  • To introduce a novel, modified Wang-Zhang algorithm for improved skeletonization outcomes.

Main Methods:

  • Training recurrent neural networks to learn pixel deletion rules for iterative thinning.
  • Implementing established algorithms like Rosenfeld-Kak and Wang-Zhang within RNN architectures.

Related Experiment Videos

  • Developing and evaluating a modified Wang-Zhang algorithm for enhanced skeleton quality.

    • Main Results:

    • RNNs successfully learn deletion rules to achieve skeletonization and thinning of binary images.
    • Presented RNN architectures effectively implement various thinning algorithms.
    • The modified Wang-Zhang algorithm produced skeletons considered more visually pleasing.

    Conclusions:

    • Recurrent neural networks offer a powerful and adaptable approach to image skeletonization and thinning.
    • The proposed modified Wang-Zhang algorithm enhances the aesthetic quality of the resulting skeletons.
    • This research opens avenues for more intuitive and efficient image analysis using deep learning.