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

Related Concept Videos

Detection of Gross Error: The Q Test

Detection of Gross Error: The Q Test

When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...

You might also read

Related Articles

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

Sort by

Same author

A Robust Multi-Branch CNN-LSTM Architecture for Cross-Subject Motor Imagery Classification.

Sensors (Basel, Switzerland)·2026

Same author

Multiscale RGB-Guided Fusion for Hyperspectral Image Super-Resolution.

Journal of imaging·2026

Same author

Enhancing Direction-of-Arrival Estimation with Multi-Task Learning.

Sensors (Basel, Switzerland)·2024

Same author

DALib: A Curated Repository of Libraries for Data Augmentation in Computer Vision.

Journal of imaging·2023

Same author

Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning.

Sensors (Basel, Switzerland)·2023

Same author

Quasi Real-Time Apple Defect Segmentation Using Deep Learning.

Sensors (Basel, Switzerland)·2023

Search research articles

Related Experiment Video

Updated: Nov 18, 2025

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

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

Published on: August 30, 2013

No Reference, Opinion Unaware Image Quality Assessment by Anomaly Detection.

Marco Leonardi¹, Paolo Napoletano¹, Raimondo Schettini¹

¹Department of Computer Science, Systems and Communications, University of Milano-Bicocca, 20126 Milan, Italy.

Sensors (Basel, Switzerland)

|February 5, 2021

Summary

This study introduces an anomaly detection method for image quality assessment using Convolutional Neural Network (CNN) feature map correlations. The approach effectively evaluates image quality by identifying deviations from pristine image characteristics.

Keywords:

Gram matrix convolutional neural network image quality assessment

More Related Videos

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Related Experiment Videos

Last Updated: Nov 18, 2025

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

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

Published on: August 30, 2013

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Area of Science:

Computer Vision
Machine Learning
Image Processing

Background:

Image quality assessment (IQA) is crucial for various applications.
Traditional IQA methods often struggle with diverse distortions.
Deep learning models offer new avenues for robust IQA.

Purpose of the Study:

To develop an anomaly detection-based IQA method.
To leverage feature map correlations from pre-trained Convolutional Neural Networks (CNNs).
To improve the accuracy and robustness of image quality evaluation.

Main Methods:

Utilizing Gram matrices to encode intra-layer feature map correlations.
Estimating quality scores by combining correlation averages and anomaly detection outputs.
Employing a dictionary of pristine images for abnormality assessment.

Main Results:

The proposed method demonstrates effectiveness on benchmark datasets (LIVE-itW, KONIQ, SPAQ).
Anomaly detection effectively quantifies image deviations from ideal quality.
Feature map correlations provide rich information for quality estimation.

Conclusions:

Anomaly detection based on CNN feature correlations offers a promising approach for IQA.
The method shows potential for real-world applications requiring reliable image quality evaluation.
Further research can explore more sophisticated correlation metrics and anomaly detection techniques.