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

You might also read

Related Articles

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

Sort by
Same author

Computational Analysis of Correlations between Image Aesthetic and Image Naturalness in the Relation with Image Quality.

Journal of imaging·2022
Same author

Time- and Resource-Efficient Time-to-Collision Forecasting for Indoor Pedestrian Obstacles Avoidance.

Journal of imaging·2021
See all related articles

Related Experiment Video

Updated: Oct 22, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.1K

Image Aesthetic Assessment Based on Image Classification and Region Segmentation.

Quyet-Tien Le1,2, Patricia Ladret1, Huu-Tuan Nguyen2

  • 1GIPSA Lab, Grenoble Alpes University, 11 rue des Mathematiques, Grenoble Campus BP 46, F-38402 Saint Martin d'Heres CEDEX, France.

Journal of Imaging
|August 30, 2021
PubMed
Summary

This study enhances image aesthetic assessment (IAA) by classifying images into categories and analyzing regions of interest (ROI). Prior classification and ROI extraction improve IAA performance, outperforming traditional methods.

Keywords:
close-up imagecolor saliency mapexifhandcrafted featuresimage aesthetic assessmentimage classificationlarge field imagelearned featuresregion of interestsharpness map

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.5K

Related Experiment Videos

Last Updated: Oct 22, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.1K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.5K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Image Aesthetic Assessment (IAA) traditionally uses uniform evaluation methods.
  • Photographic rules vary significantly across different image categories (e.g., landscapes vs. portraits).
  • Viewer attention is often focused on specific Regions of Interest (ROI) within an image.

Purpose of the Study:

  • To investigate if prior Large field/Close-up Image Classification (LCIC) improves IAA performance.
  • To determine the effectiveness of Region of Interest Extraction (ROIE) before IAA.
  • To compare handcrafted and learned features for IAA.

Main Methods:

  • Implemented LCIC to categorize images before IAA.
  • Conducted ROIE and analyzed IAA using global, ROI, and background features.
  • Compared performance using handcrafted and learned features.

Main Results:

  • Prior LCIC significantly improved IAA performance across categories.
  • ROIE was found to be beneficial, leading to a new, more effective IAA model.
  • Learned features generally outperformed handcrafted features for IAA.

Conclusions:

  • Category-specific IAA, informed by LCIC, is more effective.
  • Integrating ROIE enhances IAA accuracy.
  • Learned features offer superior performance in IAA tasks.