PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION
Blind image deconvolution/deblurring (BID) is a challenging task due to lack of prior information about the blurring process and image. Noise and ringing artefacts resulted during the restoration process further deter fine restoration of the pristine image. These artefacts mainly arise from using a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Slovenian Society for Stereology and Quantitative Image Analysis
2018-12-01
|
| Series: | Image Analysis and Stereology |
| Subjects: | |
| Online Access: | https://www.ias-iss.org/ojs/IAS/article/view/1887 |
| _version_ | 1818837377158742016 |
|---|---|
| author | Aftab Khan Hujun Yin |
| author_facet | Aftab Khan Hujun Yin |
| author_sort | Aftab Khan |
| collection | DOAJ |
| description | Blind image deconvolution/deblurring (BID) is a challenging task due to lack of prior information about the blurring process and image. Noise and ringing artefacts resulted during the restoration process further deter fine restoration of the pristine image. These artefacts mainly arise from using a poorly estimated point spread function (PSF) combined with an ineffective restoration filter. This paper presents a BID scheme based on the steepest descent in kurtosis maximization. Assuming uniform blur, the PSF can be modelled by a parametric form. The scheme tries to estimate the blur parameters by maximizing kurtosis of the deblurred image. The scheme is devised to handle any type of blur that can be framed into a parametric form such as Gaussian, motion and out-of-focus. Gradients for the blur parameters are computed and optimized in the direction of increasing kurtosis value using a steepest descent scheme. The algorithms for several common blurs are derived and the effectiveness has been corroborated through a set of experiments. Validation has also been carried out on various real examples. It is shown that the scheme optimizes on the parameters in a close vicinity of the true parameters. Results of both benchmark and real images are presented. Both full-reference and non-reference image quality measures have been used in quantifying the deblurring performance. The results show that the proposed method offers marked improvements over the existing methods. |
| first_indexed | 2024-12-19T03:21:32Z |
| format | Article |
| id | doaj.art-427d26da0f1f460a84aac0865880c0cf |
| institution | Directory Open Access Journal |
| issn | 1580-3139 1854-5165 |
| language | English |
| last_indexed | 2024-12-19T03:21:32Z |
| publishDate | 2018-12-01 |
| publisher | Slovenian Society for Stereology and Quantitative Image Analysis |
| record_format | Article |
| series | Image Analysis and Stereology |
| spelling | doaj.art-427d26da0f1f460a84aac0865880c0cf2022-12-21T20:37:45ZengSlovenian Society for Stereology and Quantitative Image AnalysisImage Analysis and Stereology1580-31391854-51652018-12-0137321322310.5566/ias.18871006PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATIONAftab Khan0Hujun Yin1University of Engineering and Technology (UET) PeshawarSchool of Electrical and Electronic Engineering The University of Manchester Manchester, UKBlind image deconvolution/deblurring (BID) is a challenging task due to lack of prior information about the blurring process and image. Noise and ringing artefacts resulted during the restoration process further deter fine restoration of the pristine image. These artefacts mainly arise from using a poorly estimated point spread function (PSF) combined with an ineffective restoration filter. This paper presents a BID scheme based on the steepest descent in kurtosis maximization. Assuming uniform blur, the PSF can be modelled by a parametric form. The scheme tries to estimate the blur parameters by maximizing kurtosis of the deblurred image. The scheme is devised to handle any type of blur that can be framed into a parametric form such as Gaussian, motion and out-of-focus. Gradients for the blur parameters are computed and optimized in the direction of increasing kurtosis value using a steepest descent scheme. The algorithms for several common blurs are derived and the effectiveness has been corroborated through a set of experiments. Validation has also been carried out on various real examples. It is shown that the scheme optimizes on the parameters in a close vicinity of the true parameters. Results of both benchmark and real images are presented. Both full-reference and non-reference image quality measures have been used in quantifying the deblurring performance. The results show that the proposed method offers marked improvements over the existing methods.https://www.ias-iss.org/ojs/IAS/article/view/1887blind image deblurring (BID)gradient descentimage quality measures (IQMs)image restorationkurtosis |
| spellingShingle | Aftab Khan Hujun Yin PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION Image Analysis and Stereology blind image deblurring (BID) gradient descent image quality measures (IQMs) image restoration kurtosis |
| title | PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION |
| title_full | PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION |
| title_fullStr | PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION |
| title_full_unstemmed | PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION |
| title_short | PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION |
| title_sort | parametric blind image deblurring with gradient based spectral kurtosis maximization |
| topic | blind image deblurring (BID) gradient descent image quality measures (IQMs) image restoration kurtosis |
| url | https://www.ias-iss.org/ojs/IAS/article/view/1887 |
| work_keys_str_mv | AT aftabkhan parametricblindimagedeblurringwithgradientbasedspectralkurtosismaximization AT hujunyin parametricblindimagedeblurringwithgradientbasedspectralkurtosismaximization |