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

A deep learning method for predicting the minimum inhibitory concentration of antimicrobial peptides against <i>Escherichia coli</i> using Multi-Branch-CNN and Attention.

mSystems·2023
Same author

A feature transferring workflow between data-poor compounds in various tasks.

PloS one·2022
Same author

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert-Huang Transform and Deep Learning.

Sensors (Basel, Switzerland)·2020
Same author

Convolutional Neural Networks-Based Object Detection Algorithm by Jointing Semantic Segmentation for Images.

Sensors (Basel, Switzerland)·2020

Related Experiment Video

Updated: Sep 9, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.1K

A Style Transfer-Based Fast Image Quality Assessment Method for Image Sensors.

Weizhi Xian1,2, Bin Chen1,3, Jielu Yan4

  • 1Chongqing Research Institute of Harbin Institute of Technology, Harbin Institute of Technology, Chongqing 401151, China.

Sensors (Basel, Switzerland)
|August 28, 2025
PubMed
Summary

A new method for image quality assessment, Style- and Content-based IQA (SCIQA), uses deep learning and style transfer principles. SCIQA outperforms existing methods in accuracy and generalizability for evaluating visual data fidelity.

Keywords:
full referenceimage contentimage quality assessmentperceptual distancestyle transfer

More Related Videos

Fast Inspection of Quality of Indigo Naturalis by Multiple Light Scattering
03:40

Fast Inspection of Quality of Indigo Naturalis by Multiple Light Scattering

Published on: August 18, 2023

511
Label-Free Imaging of Single Proteins Secreted from Living Cells via iSCAT Microscopy
10:55

Label-Free Imaging of Single Proteins Secreted from Living Cells via iSCAT Microscopy

Published on: November 20, 2018

17.4K

Related Experiment Videos

Last Updated: Sep 9, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.1K
Fast Inspection of Quality of Indigo Naturalis by Multiple Light Scattering
03:40

Fast Inspection of Quality of Indigo Naturalis by Multiple Light Scattering

Published on: August 18, 2023

511
Label-Free Imaging of Single Proteins Secreted from Living Cells via iSCAT Microscopy
10:55

Label-Free Imaging of Single Proteins Secreted from Living Cells via iSCAT Microscopy

Published on: November 20, 2018

17.4K

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Accurate image quality evaluation is crucial for optimizing sensor performance and visual data fidelity.
  • Image style, encompassing visual characteristics like color and texture, significantly impacts perceived quality.

Purpose of the Study:

  • To propose a novel full-reference image quality assessment (FR-IQA) method named Style- and Content-based IQA (SCIQA).
  • To develop a method that integrates image content and style for more accurate perceptual quality assessment.

Main Methods:

  • Utilized a deep convolutional neural network (CNN) for image feature decomposition in the deep domain.
  • Defined a deep perceptual distance metric combining content-based and style-based measures.
  • Formulated a perceptual optimization problem solved via convex optimization for model parameter tuning.

Main Results:

  • SCIQA demonstrated superior performance over state-of-the-art FR-IQA methods on multiple benchmark datasets (LIVE, CSIQ, TID2013, KADID-10k, PIPAL).
  • Achieved high Pearson linear correlation coefficients (PLCC) (e.g., 0.956 on LIVE) and robust generalizability (SROCC of 0.702 on PIPAL).
  • Outperformed traditional (SSIM) and deep learning-based (DISTS) methods in accuracy.

Conclusions:

  • SCIQA offers exceptional prediction accuracy, strong interpretability, and low computational complexity.
  • The proposed method is a practical and effective tool for real-world image quality assessment applications.