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

Upsampling01:22

Upsampling

214
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
214
Time and frequency -Domain Interpretation of PI Control01:27

Time and frequency -Domain Interpretation of PI Control

112
Proportional-Integral (PI) controllers are essential in many control systems to improve stability and performance. They are commonly used in everyday devices like thermostats to enhance system damping and reduce steady-state error. When the zero in the controller's transfer function is optimally placed, the system benefits significantly in terms of stability and accuracy.
Acting as a low-pass filter, the PI controller slows the system's response and extends settling times. This requires...
112
PD Controller: Design01:26

PD Controller: Design

199
In automotive engineering, car suspension systems often employ Proportional Derivative (PD) controllers to enhance performance. PD controllers are utilized to adjust the damping force in response to road conditions. A controller, acting as an amplifier with a constant gain, demonstrates proportional control, with output directly mirroring input.
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
199
PI Controller: Design01:24

PI Controller: Design

222
Proportional Integral (PI) controllers are a fundamental component in modern control systems, widely used to enhance performance and mitigate steady-state errors. They are particularly effective in applications such as automatic brightness adjustment on smartphones, where they excel at mitigating steady-state errors for step-function inputs. Unlike PD controllers, which require time-varying errors to function optimally, PI controllers leverage their integral component to address residual...
222
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

179
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
179

You might also read

Related Articles

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

Sort by
Same author

Synthesis, Characterization, and Photovoltaic Performance of Porphyrin-Fullerene Dyads.

The Journal of organic chemistry·2026
Same author

Delayed Detection of Atrial Fibrillation After Cryptogenic Stroke and Risk of Recurrent Ischemic Stroke: A Retrospective Cohort Study.

Annals of Indian Academy of Neurology·2026
Same author

Large and regional-scale processes influencing Heat Waves: Insights from Qatar.

Scientific reports·2026
Same author

A Descriptive Analysis of GP Referrals to a Model 4 Emergency Department in the West of Ireland.

Irish journal of medical science·2026
Same author

Functionalized porphyrin-fullerene dyads: a pathway to the enhanced performance of perovskite solar cells.

Organic & biomolecular chemistry·2026
Same author

Transfer of sediment-derived carbon into aquatic plants for <sup>14</sup>C biosphere assessment.

Radiation and environmental biophysics·2026

Related Experiment Video

Updated: Jun 12, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Design of compensation algorithms for zero padding and its application to a patch based deep neural network.

Safi Ullah1,2, Seong-Ho Song1

  • 1Division of Software, Hallym University, Chuncheon, Gangwon-do, Republic of Korea.

Peerj. Computer Science
|September 24, 2024
PubMed
Summary

New compensation algorithms for zero padding improve deep convolutional neural network performance by correcting errors in convolutional outputs. These methods enhance single image super-resolution and lung CT image segmentation tasks.

Keywords:
Adaptive PCPConvolution filterPartial convolution based paddingSRResNetSigned PCPZero padded input

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

377
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

485

Related Experiment Videos

Last Updated: Jun 12, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

377
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

485

Area of Science:

  • Computer Vision
  • Deep Learning
  • Image Processing

Background:

  • Deep convolutional neural networks (CNNs) are powerful tools for image processing tasks.
  • Zero padding is commonly used in CNNs but can introduce artifacts and errors.
  • Existing methods like partial convolution based padding (PCP) have limitations.

Purpose of the Study:

  • To develop novel compensation algorithms for zero padding in CNNs.
  • To enhance the performance of CNNs by mitigating zero padding errors.
  • To demonstrate the generalizability of these algorithms across different tasks.

Main Methods:

  • Proposed compensation algorithms consider the characteristics of convolving filters.
  • Algorithms are developed to correct convolutional output errors caused by zero-padded inputs.
  • Methods are initially applied to SRResNet for single image super-resolution.
  • Efficacy is further tested on U-Net for lung CT image segmentation.

Main Results:

  • The proposed algorithms demonstrate superior performance compared to existing methods.
  • Significant performance improvements were observed in both single image super-resolution and lung CT image segmentation.
  • The algorithms effectively compensate for errors introduced by zero padding.

Conclusions:

  • The developed compensation algorithms offer a significant advancement in CNN performance.
  • These methods provide a generalized solution for addressing zero padding issues in various CNN architectures and applications.
  • The findings suggest a new standard for handling zero padding in deep learning image processing.