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 Concept Videos

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

1.3K
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
1.3K

You might also read

Related Articles

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

Sort by
Same author

An autopsy-based study on child mortality under six in Taiwan: Forensic autopsy findings and the complexities of causal determination.

Journal of the Formosan Medical Association = Taiwan yi zhi·2026
Same author

Molecular Imaging in Primary Aldosteronism Subtyping: A Promising Complement but Not Yet a Replacement for Adrenal Venous Sampling.

Journal of the American Heart Association·2026
Same author

High-Payload and Secure Data Hiding for Medical Images in IoMT-Based eHealth Systems.

Sensors (Basel, Switzerland)·2026
Same author

Multimodal Navigation System for Visually Impaired Users Using Environmental Perception and Vision-Language Models.

Sensors (Basel, Switzerland)·2026
Same author

Renin-Guided Risk Stratification and Therapy in Hypertension to Reduce Major Adverse Cardiovascular Outcomes.

medRxiv : the preprint server for health sciences·2026
Same author

NT-proBNP and its association with autonomous aldosterone production in primary aldosteronism.

Therapeutic advances in endocrinology and metabolism·2026

Related Experiment Video

Updated: May 6, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K

Sand Painting Generation Based on Convolutional Neural Networks.

Chin-Chen Chang1, Ping-Hao Peng1

  • 1Department of Computer Science and Information Engineering, National United University, Miaoli 36003, Taiwan.

Journal of Imaging
|February 23, 2024
PubMed
Summary

This study introduces a convolutional neural network approach for neural style transfer to generate sand paintings. The method enhances sand painting quality by reducing blur and background noise, improving visual effects.

Keywords:
edge detectionmorphologyneural style transfersand painting

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

537
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

401

Related Experiment Videos

Last Updated: May 6, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

537
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

401

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Digital Art

Background:

  • Neural style transfer (NST) is a technique for image generation.
  • Traditional sand painting generation can suffer from blurred objects and background noise.
  • Improving the quality and efficiency of digital sand painting is an ongoing challenge.

Purpose of the Study:

  • To propose a novel neural style transfer approach for sand painting generation.
  • To enhance sand painting quality by addressing object blur and background noise.
  • To improve the visual fidelity of sand paintings using deep learning.

Main Methods:

  • Image segmentation to isolate main objects from content images.
  • Close-open filtering for image smoothing.
  • Sobel edge detection to generate edge maps.
  • Convolutional neural network-based neural style transfer using edge maps and a style image.
  • Integration of generated components for the final sand painting.

Main Results:

  • The proposed approach successfully generates sand painting images with good visual effects.
  • The method effectively reduces object blur and background noise compared to existing techniques.
  • Qualitative assessment indicates superior visual outcomes for sand painting generation.

Conclusions:

  • The developed neural style transfer method offers an effective solution for high-quality sand painting generation.
  • This approach advances the application of deep learning in digital art creation.
  • The technique provides a significant improvement over previous methods for sand painting synthesis.