Search research articles

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: Apr 11, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Image Quality Assessment Using Human Visual DOG Model Fused With Random Forest.

Soo-Chang Pei, Li-Heng Chen

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|June 9, 2015

Summary

A new method for objective image quality assessment (IQA) uses Difference of Gaussian features to predict image quality, aligning with human perception. This approach enhances multimedia applications by providing more accurate and robust quality metrics.

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

Vertebral trabecular microarchitecture changes in the normally ageing population.

Quantitative imaging in medicine and surgery·2026

Same author

Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Same author

Multi-modal antibacterial lignin-based nanocomposites with photothermal and free radical therapy for bacterial infection treatment.

International journal of biological macromolecules·2025

Same author

Treatment of refractory anti-melanoma differentiation-associated gene 5 anbibody-positive dermatomyositis complicated by rapidly progressing interstitial pulmonary disease: Two case reports.

World journal of clinical cases·2023

Same author

Solar X-ray and EUV imager on board the FY-3E satellite.

Light, science & applications·2022

Same author

Perceptual Video Quality Prediction Emphasizing Chroma Distortions.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2020

Area of Science:

Computer Vision
Image Processing
Human-Computer Interaction

Background:

Objective image quality assessment (IQA) is crucial for multimedia applications.
Existing IQA metrics struggle with newer databases like TID2013.
Human perception consistency is a key challenge in IQA.

Purpose of the Study:

To develop a novel methodology for building an IQA metric model.
To create an IQA score that accurately mimics human visual perception (HVS).
To address the limitations of current IQA metrics against challenging datasets.

Main Methods:

A regression approach was employed to build the metric model.
Features were extracted from Difference of Gaussians (DOG) frequency bands.

More Related Videos

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Related Experiment Videos

Last Updated: Apr 11, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

A random forest regression model was trained using the proposed DOG features.

Main Results:

The proposed IQA score is a nonlinear combination of DOG frequency band features.
The developed model demonstrates high correspondence with human visual perception.
The model shows robustness when tested on available IQA databases.

Conclusions:

The novel DOG feature-based regression model offers improved IQA performance.
The methodology effectively mimics the human visual system for quality prediction.
This approach provides a robust and perceptually relevant solution for objective IQA.