Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images
Remote sensing images are subject to different types of degradations. The visual quality of such images is important because their visual inspection and analysis are still widely used in practice. To characterize the visual quality of remote sensing images, the use of specialized visual quality metr...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/15/2349 |
_version_ | 1797561649445470208 |
---|---|
author | Oleg Ieremeiev Vladimir Lukin Krzysztof Okarma Karen Egiazarian |
author_facet | Oleg Ieremeiev Vladimir Lukin Krzysztof Okarma Karen Egiazarian |
author_sort | Oleg Ieremeiev |
collection | DOAJ |
description | Remote sensing images are subject to different types of degradations. The visual quality of such images is important because their visual inspection and analysis are still widely used in practice. To characterize the visual quality of remote sensing images, the use of specialized visual quality metrics is desired. Although the attempts to create such metrics are limited, there is a great number of visual quality metrics designed for other applications. Our idea is that some of these metrics can be employed in remote sensing under the condition that those metrics have been designed for the same distortion types. Thus, image databases that contain images with types of distortions that are of interest should be looked for. It has been checked what known visual quality metrics perform well for images with such degradations and an opportunity to design neural network-based combined metrics with improved performance has been studied. It is shown that for such combined metrics, their Spearman correlation coefficient with mean opinion score exceeds 0.97 for subsets of images in the Tampere Image Database (TID2013). Since different types of elementary metric pre-processing and neural network design have been considered, it has been demonstrated that it is enough to have two hidden layers and about twenty inputs. Examples of using known and designed visual quality metrics in remote sensing are presented. |
first_indexed | 2024-03-10T18:17:54Z |
format | Article |
id | doaj.art-6e76af32e01c48e6825e56bd2ab3c1f9 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T18:17:54Z |
publishDate | 2020-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-6e76af32e01c48e6825e56bd2ab3c1f92023-11-20T07:33:07ZengMDPI AGRemote Sensing2072-42922020-07-011215234910.3390/rs12152349Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing ImagesOleg Ieremeiev0Vladimir Lukin1Krzysztof Okarma2Karen Egiazarian3Department of Information and Communication Technologies, National Aerospace University, 61070 Kharkov, UkraineDepartment of Information and Communication Technologies, National Aerospace University, 61070 Kharkov, UkraineDepartment of Signal Processing and Multimedia Engineering, West Pomeranian University of Technology in Szczecin, 70-313 Szczecin, PolandComputational Imaging Group, Tampere University, 33720 Tampere, FinlandRemote sensing images are subject to different types of degradations. The visual quality of such images is important because their visual inspection and analysis are still widely used in practice. To characterize the visual quality of remote sensing images, the use of specialized visual quality metrics is desired. Although the attempts to create such metrics are limited, there is a great number of visual quality metrics designed for other applications. Our idea is that some of these metrics can be employed in remote sensing under the condition that those metrics have been designed for the same distortion types. Thus, image databases that contain images with types of distortions that are of interest should be looked for. It has been checked what known visual quality metrics perform well for images with such degradations and an opportunity to design neural network-based combined metrics with improved performance has been studied. It is shown that for such combined metrics, their Spearman correlation coefficient with mean opinion score exceeds 0.97 for subsets of images in the Tampere Image Database (TID2013). Since different types of elementary metric pre-processing and neural network design have been considered, it has been demonstrated that it is enough to have two hidden layers and about twenty inputs. Examples of using known and designed visual quality metrics in remote sensing are presented.https://www.mdpi.com/2072-4292/12/15/2349image quality assessmentvisual quality metricsneural networkscombined metrics |
spellingShingle | Oleg Ieremeiev Vladimir Lukin Krzysztof Okarma Karen Egiazarian Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images Remote Sensing image quality assessment visual quality metrics neural networks combined metrics |
title | Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images |
title_full | Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images |
title_fullStr | Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images |
title_full_unstemmed | Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images |
title_short | Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images |
title_sort | full reference quality metric based on neural network to assess the visual quality of remote sensing images |
topic | image quality assessment visual quality metrics neural networks combined metrics |
url | https://www.mdpi.com/2072-4292/12/15/2349 |
work_keys_str_mv | AT olegieremeiev fullreferencequalitymetricbasedonneuralnetworktoassessthevisualqualityofremotesensingimages AT vladimirlukin fullreferencequalitymetricbasedonneuralnetworktoassessthevisualqualityofremotesensingimages AT krzysztofokarma fullreferencequalitymetricbasedonneuralnetworktoassessthevisualqualityofremotesensingimages AT karenegiazarian fullreferencequalitymetricbasedonneuralnetworktoassessthevisualqualityofremotesensingimages |