No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics

Blurring is one of the most common distortions in digital images. In the past decade, extensive image deblurring algorithms have been proposed to restore a latent clean image from its blurred version. However, very little work has been dedicated to the quality assessment of deblurred images, which m...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Leida, Yan, Ya, Lu, Zhaolin, Wu, Jinjian, Gu, Ke, Wang, Shiqi
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/87058
http://hdl.handle.net/10220/44298
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-87058
record_format dspace
spelling sg-ntu-dr.10356-870582020-03-07T11:48:51Z No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics Li, Leida Yan, Ya Lu, Zhaolin Wu, Jinjian Gu, Ke Wang, Shiqi School of Computer Science and Engineering School of Electrical and Electronic Engineering Image Quality Assessment Defocus Deblurring Blurring is one of the most common distortions in digital images. In the past decade, extensive image deblurring algorithms have been proposed to restore a latent clean image from its blurred version. However, very little work has been dedicated to the quality assessment of deblurred images, which may hinder further development of more advanced deblurring techniques. Motivated by this, this paper presents a no-reference quality metric for defocus deblured images based on Natural Scene Statistics (NSS). Two categories of NSS features are extracted in both the spatial and frequency domains to account for both the global and local aspects of distortions in deblurred images. Specifically, the spatial domain NSS features are used to characterize the global naturalness, and the frequency domain NSS features are used to portray the local structural distortions. All features are combined to train a support vector regression model for quality prediction of defocus deblurred images. The performance of the proposed metric is evaluated in a subjectively rated defocus deblurred image database. The experimental results demonstrate the advantages of the proposed metric over the relevant state-of-the-arts. As an application, the proposed metric is further used for benchmarking deblurring algorithms and very encouraging results are achieved. Published version 2018-01-10T04:24:53Z 2019-12-06T16:34:13Z 2018-01-10T04:24:53Z 2019-12-06T16:34:13Z 2017 Journal Article Li, L., Yan, Y., Lu, Z., Wu, J., Gu, K., & Wang, S. (2017). No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics. IEEE Access, 5, 2163-2171. https://hdl.handle.net/10356/87058 http://hdl.handle.net/10220/44298 10.1109/ACCESS.2017.2661858 en IEEE Access © 2017 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information 9 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Image Quality Assessment
Defocus Deblurring
spellingShingle Image Quality Assessment
Defocus Deblurring
Li, Leida
Yan, Ya
Lu, Zhaolin
Wu, Jinjian
Gu, Ke
Wang, Shiqi
No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
description Blurring is one of the most common distortions in digital images. In the past decade, extensive image deblurring algorithms have been proposed to restore a latent clean image from its blurred version. However, very little work has been dedicated to the quality assessment of deblurred images, which may hinder further development of more advanced deblurring techniques. Motivated by this, this paper presents a no-reference quality metric for defocus deblured images based on Natural Scene Statistics (NSS). Two categories of NSS features are extracted in both the spatial and frequency domains to account for both the global and local aspects of distortions in deblurred images. Specifically, the spatial domain NSS features are used to characterize the global naturalness, and the frequency domain NSS features are used to portray the local structural distortions. All features are combined to train a support vector regression model for quality prediction of defocus deblurred images. The performance of the proposed metric is evaluated in a subjectively rated defocus deblurred image database. The experimental results demonstrate the advantages of the proposed metric over the relevant state-of-the-arts. As an application, the proposed metric is further used for benchmarking deblurring algorithms and very encouraging results are achieved.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Li, Leida
Yan, Ya
Lu, Zhaolin
Wu, Jinjian
Gu, Ke
Wang, Shiqi
format Article
author Li, Leida
Yan, Ya
Lu, Zhaolin
Wu, Jinjian
Gu, Ke
Wang, Shiqi
author_sort Li, Leida
title No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
title_short No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
title_full No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
title_fullStr No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
title_full_unstemmed No-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
title_sort no-reference quality assessment of deblurred images based on natural scene statistics
publishDate 2018
url https://hdl.handle.net/10356/87058
http://hdl.handle.net/10220/44298
_version_ 1681038757265932288