PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION

Authors

  • Aftab Khan University of Engineering and Technology (UET) Peshawar
  • Hujun Yin School of Electrical and Electronic Engineering The University of Manchester Manchester, UK

DOI:

https://doi.org/10.5566/ias.1887

Keywords:

blind image deblurring (BID), gradient descent, image quality measures (IQMs), image restoration, kurtosis

Abstract

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.

Author Biographies

Aftab Khan, University of Engineering and Technology (UET) Peshawar

Dr. Aftab Khan is working as assistant professor in Department of Computer Systems Engineering (DCSE), University of Engineering and Technology (UET), Peshawar since Dec 2013. He received his B.E. degree in computer system engineering in 2009 from College of Electrical and Mechanical Engineering, a constituent college of National University of Sciences and Technology (NUST), Islamabad, Pakistan.

Afterwards, he completed his PhD research study in "Single-Image Blind Deblurring and Restoration Techniques" from The University of Manchester, UK in 2014. Dr. Khan was a recipient of the faculty development scholarship from the University of Engineering and Technology (UET), Peshawar, Pakistan for his PhD research study. From 2010 to 2013, he was also a Graduate Teaching Assistant with The University of Manchester, UK.

His image restoration expertise includes restoration of blurred images using blind deblurring techniques based on non-reference image quality measures. His image processing skills include OCT image denoising, medical image analysis and image fusion. His research interests include digital image restoration, blind image deblurring, medical image processing and digital image and video compression. 

Hujun Yin, School of Electrical and Electronic Engineering The University of Manchester Manchester, UK

Hujun Yin received BEng and MSc degrees from Southeast University and PhD degree from University of York, respectively. He jointed the University of Manchester (UMIST before the merge) in 1996 as a Post-Doc Research Associate. He was appointed Lecturer in 1998 and became a Senior Lecturer in 2003. 

He is a senior member of the IEEE and a member of the EPSRC Peer Review College.

He gave a plenary talk to SOCO 2017, HAIS 2013, IEEE IST 2012, CBIC 2011 and HAIS 2008 and was a Tutorial Speaker at WCCI 2008 (Title: Nonlinear Dimensionality Reduction and Data Visualisation). He was the chair of Special Session on Principal Manifolds and Data Visualisation at IJCNN 2007. An organiser of Biologically Inspired Information Fusion Workshop, Surrey, 22-23 August 2006. A talk on "The Self-Organising Maps for Data Visualisation and Manifold Mapping" to Workshop on Principal Manifolds, Leicester, 24-26 August 2006. 

He has been an Associate Editor for IEEE Transactions on Cybernetics since 2015 and was an Associate Editor for IEEE Transactions on Neural Networks between 2006-2009. He has been a member of Editorial Board of International Journal of Neural Systems since 2005.

More information can be found and some publications can be downloaded fromhttp://personalpages.manchester.ac.uk/staff/hujun.yin

References

Banham, M. R. and A. K. Katsaggelos (1997). "Digital Image Restoration." IEEE Signal Processing Magazine 14(2): 24-41.

Biemond, J., et al. (1990). "Iterative Methods for Image Deblurring." Proceedings of the IEEE 78(5): 856-883.

Brunet, D., et al. (2012). "On the Mathematical Properties of the Structural Similarity Index." IEEE Transactions on Image Processing 21(4): 1488-1499.

Chan, T. F. and C. K. Wong (1998). "Total Variation Blind Deconvolution." IEEE Transactions on Image Processing 7(3): 370-375.

Chen, D. and L. Cheng (2011). "Alternative minimisation algorithm for non-local total variational image deblurring." IET Image Processing 4(5): 353-364.

Cho, S. and S. Lee (2009). "Fast Motion Deblurring." ACM Transactions on Graphics 28(5).

Frank, W. O., et al. (2010). NIST Handbook of Mathematical Functions, Cambridge University Press: 966.

Gao, Y., et al. (2011). CW-SSIM Based Image Classification. 18th IEEE International Conference on Image Processing. New York, IEEE: 1249-1252.

Gupta, A., et al. (2010). Single Image Deblurring Using Motion Density Functions. 11th European Conference on Computer Vision. K. Daniilidis, P. Maragos and N. Paragios. Heraklion, Crete, Greece, Springer-Verlag Berlin. 6311: 171-184.

Hirsch, M., et al. (2011). Fast Removal of Non-uniform Camera Shake. International Conference on Computer Vision. New York, IEEE: 463-470.

Khan, A. and H. Yin (2011). Spectral Non-Gaussianity for Blind Image Deblurring. Proceedings of the 12th international conference on Intelligent Data Engineering and Automated Learning Norwich, UK, Springer-Verlag.

Kundur, D. and D. Hatzinakos (1996). "Blind Image Deconvolution." IEEE Signal Processing Magazine 13(3): 43-64.

Kundur, D. and D. Hatzinakos (1998). "A Novel Blind Deconvolution Scheme for Image Restoration Using Recursive Filtering." IEEE Transactions on Signal Processing 46(2): 375-390.

Lagendijk, R. L. and J. Biemond (2009). Basic Methods for Image Restoration and Identification. The Essential Guide to Image Processing. San Diego, Academic Press USA: 323-348.

Lagendijk, R. L., et al. (1988). "Regularized Iterative Image-Restoration with Ringing Reduction." IEEE Transactions on Acoustics Speech and Signal Processing 36(12): 1874-1888.

Lagendijk, R. L., et al. (1990). "Maximum-Likelihood Image and Blur Identification - A Unifying Approach." Optical Engineering 29(5): 422-435.

Lu, C. W. (2012). "Image restoration and decomposition using nonconvex non-smooth regularisation and negative Hilbert–Sobolev norm." IET Image Processing: pp. 706–716.

Mittal, A., et al. (2011). BRISQUE Software Release.

Mittal, A., et al. (2012). "NIQE Software Release." from http://live.ece.utexas.edu/research/quality/niqe.zip.

Mittal, A., et al. (2012). "No-Reference Image Quality Assessment in the Spatial Domain." IEEE Transactions on Image Processing 21(12): 4695-4708.

Mittal, A., et al. (2013). "Making a "Completely Blind" Image Quality Analyzer." IEEE Signal Processing Letters 20(3): 209-212.

Nexus, D. "Desktop Nexus Wallpaper Image Database." from http://www.desktopnexus.com/.

Oppenheim, A. V., et al. (1968). "Nonlinear Filtering Of Multiplied and Convolved Signals." Proceedings of the IEEE 56(8): 1264-1285.

Rehman, A. and Z. Wang (2011). SSIM-Based Non-Local Means Image Denoising. 18th IEEE International Conference on Image Processing. New York, IEEE: 217-220.

Richardson, W. H. (1972). "Bayesian-Based Iterative Method of Image Restoration." Journal of the Optical Society of America 62(1): 55-59.

Shan, Q., et al. (2008). "High-Quality Motion Deblurring From a Single Image." ACM Transactions on Graphics 27(3): 10.

Sondhi, M. M. (1972). "Image Restoration - Removal of Spatially Invariant Degradations." Proceedings of the IEEE 60(7): 842-853.

Szolgay, D. and T. T. Szirányi (2011). "Optimal stopping condition for iterative image deconvolution by new orthogonality criterion." Electronics Letters 47(7): 442-444.

Wang, Z. and A. C. Bovik (2002). "A Universal Image Quality Index." IEEE Signal Processing Letters 9(3): 81-84.

Wang, Z., et al. (2004). "Image quality assessment: From error visibility to structural similarity." IEEE Transactions on Image Processing 13(4): 600-612.

Wang, Z. and Q. Li (2011). "Information Content Weighting for Perceptual Image Quality Assessment." IEEE Transactions on Image Processing 20(5): 1185-1198.

Whyte, O., et al. (2011). Deblurring Shaken and Partially Saturated Images. International Conference on Computer Vision Workshops. New York, IEEE.

Wiggins, R. A. (1978). "Minimum Entropy Deconvolution." Geoexploration 16(1-2): 21-35.

Yang, S. X. and B. Y. Liu (2011). "Image deblurring using weighted total variation regularisation for half-quadratic model." Electronics Letters 47(22).

Yin, H. J. and I. Hussain (2008). "Independent Component Analysis and Non-Gaussianity for Blind Image Deconvolution and Deblurring." Integrated Computer-Aided Engineering 15(3): 219-228.

Yuquan, X., et al. (2013). Single-Image Blind Deblurring for Non-Uniform Camera-Shake Blur. Proceedings of the 11th Asian conference on Computer Vision Daejeon, Korea, Springer-Verlag. 3: 336-348.

Downloads

Published

2018-12-06

How to Cite

Khan, A., & Yin, H. (2018). PARAMETRIC BLIND IMAGE DEBLURRING WITH GRADIENT BASED SPECTRAL KURTOSIS MAXIMIZATION. Image Analysis and Stereology, 37(3), 213–223. https://doi.org/10.5566/ias.1887

Issue

Vol. 37 No. 3 (2018)

Section

Original Research Paper

License

Copyright (c) 2018 Image Analysis & Stereology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.