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: May 31, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

A Comprehensive Survey of Deep Learning Approaches in Image Processing.

Maria Trigka1, Elias Dritsas1

  • 1Industrial Systems Institute (ISI), Athena Research and Innovation Center, 26504 Patras, Greece.

Sensors (Basel, Switzerland)
|January 25, 2025
PubMed
Summary

Deep learning (DL) has revolutionized image processing, offering advanced capabilities beyond traditional methods. This survey explores DL

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

A Comprehensive Survey of Machine Learning Techniques and Models for Object Detection.

Sensors (Basel, Switzerland)·2025
Same author

Efficient Data-Driven Machine Learning Models for Cardiovascular Diseases Risk Prediction.

Sensors (Basel, Switzerland)·2023
Same author

Long-Term Coronary Artery Disease Risk Prediction with Machine Learning Models.

Sensors (Basel, Switzerland)·2023
Same author

Supervised Machine Learning Models to Identify Early-Stage Symptoms of SARS-CoV-2.

Sensors (Basel, Switzerland)·2023
Same author

An Efficient Distributed Approach for Cooperative Spectrum Sensing in Varying Interests Cognitive Radio Networks.

Sensors (Basel, Switzerland)·2022
Same author

Non-Linear Observer Design with Laguerre Polynomials.

Entropy (Basel, Switzerland)·2022

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Image Processing

Background:

  • Traditional image processing methods have limitations in handling complex visual data.
  • Deep learning (DL) approaches have emerged as powerful tools for image analysis and interpretation.
  • The evolution of DL architectures and learning paradigms has significantly enhanced image processing capabilities.

Purpose of the Study:

  • To provide a comprehensive survey of deep learning approaches in image processing.
  • To analyze the evolution of DL architectures and learning paradigms for visual data.
  • To identify key advancements, evaluation metrics, and future directions in DL for image processing.

Main Methods:

  • In-depth exploration of DL techniques applied to image processing.
Keywords:
deep learningimage processingmetricsmodelstechniques

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

455
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

363

Related Experiment Videos

Last Updated: May 31, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K
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

455
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

363
  • Analysis of architectural designs and learning paradigms in DL for image processing.
  • Review of model efficiency, generalization, robustness, and evaluation metrics.

    • Main Results:

    • DL has redefined image processing, enabling capabilities beyond traditional methods.
    • Key advancements focus on improving model efficiency, generalization, and robustness for complex tasks.
    • DL effectively tackles sophisticated image-processing challenges across diverse domains.

    Conclusions:

    • Deep learning significantly enhances the ability to process and interpret complex visual data.
    • Future directions include integrating quantum computing, neuromorphic architectures, federated learning, edge computing, and explainable AI (AI).
    • These integrations promise to further extend DL capabilities, driving innovation in image processing.