Search research articles

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

Automatic Tuning of Gaussian Filter for Image Vignetting Correction.

Sensors (Basel, Switzerland)·2026

Same author

Superpixel-Based PSO Algorithms for Color Image Quantization.

Sensors (Basel, Switzerland)·2023

Same author

Image Vignetting Correction Using a Deformable Radial Polynomial Model.

Sensors (Basel, Switzerland)·2023

Same author

Efficient Color Quantization Using Superpixels.

Sensors (Basel, Switzerland)·2022

Same author

A Smooth Non-Iterative Local Polynomial (SNILP) Model of Image Vignetting.

Sensors (Basel, Switzerland)·2021

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Blind Image Quality Assessment Using Convolutional Neural Networks.

Mariusz Frackiewicz¹, Henryk Palus¹, Wojciech Trojanowski¹

¹Department of Data Science and Engineering, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland.

Sensors (Basel, Switzerland)

|November 27, 2025

Summary

This study introduces a lightweight convolutional neural network (CNN) model for blind image quality assessment (BIQA). By using advanced machine learning optimization, it achieves competitive performance with greater efficiency and scalability than complex deep learning methods.

Keywords:

convolutional neural network deep learning image database image quality assessment

More Related Videos

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

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

Published on: November 30, 2022

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 10, 2026

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

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

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

Published on: November 30, 2022

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

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

Published on: December 15, 2023

Area of Science:

Computer Vision
Multimedia Processing
Machine Learning

Background:

Image quality is crucial for multimedia tasks like compression and transmission.
Current blind image quality assessment (BIQA) methods often use complex deep learning models, demanding significant computational resources and large datasets.
This complexity hinders scalability and deployment in resource-limited scenarios.

Purpose of the Study:

To demonstrate that a simpler, lightweight convolutional neural network (CNN) architecture can achieve competitive performance in blind image quality assessment (BIQA).
To leverage recent machine learning advancements, including Bayesian hyperparameter optimization and Adam, to enhance a revisited early CNN model for BIQA.
To offer a more scalable and efficient alternative to current complex deep learning-based BIQA methods.

Main Methods:

Revisiting an early CNN-inspired model for BIQA.
Incorporating modern machine learning optimization techniques: Bayesian hyperparameter optimization and the Adam stochastic optimization method.
Conducting extensive experiments on benchmark datasets like TID2013 and KADID-10k for evaluation.

Main Results:

The proposed lightweight CNN model achieves competitive performance in blind image quality assessment (BIQA).
The model demonstrates a substantially more efficient design compared to existing complex frameworks.
Experimental results validate the effectiveness of the approach on standard datasets.

Conclusions:

Lightweight CNN-based models, enhanced by modern optimization strategies, offer a viable alternative for BIQA.
These models provide an improved balance between accuracy, computational efficiency, and scalability.
The findings suggest a practical approach for deploying effective BIQA in resource-constrained environments.