Tchebichef moment based restoration of Gaussian blurred images.

With the knowledge of how edges vary in the presence of a Gaussian blur, a method that uses low-order Tchebichef moments is proposed to estimate the blur parameters: sigma (σ) and size (w). The difference between the Tchebichef moments of the original and the reblurred images is used as feature vectors to train an extreme learning machine for estimating the blur parameters (σ,w). The effectiveness of the proposed method to estimate the blur parameters is examined using cross-database validation. The estimated blur parameters from the proposed method are used in the split Bregman-based image restoration algorithm. A comparative analysis of the proposed method with three existing methods using all the images from the LIVE database is carried out. The results show that the proposed method in most of the cases performs better than the three existing methods in terms of the visual quality evaluated using the structural similarity index.

[1]  Nikolas P. Galatsanos,et al.  A variational approach for Bayesian blind image deconvolution , 2004, IEEE Transactions on Signal Processing.

[2]  Haibo Wang,et al.  Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine , 2014, IEEE Journal of Biomedical and Health Informatics.

[3]  Wen Gao,et al.  Group-Based Sparse Representation for Image Restoration , 2014, IEEE Transactions on Image Processing.

[4]  Piet B. W. Schwering,et al.  Turbulence compensation: an overview , 2012, Defense, Security, and Sensing.

[5]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[6]  Cécile Barat,et al.  Scale-adaptive detection and local characterization of edges based on wavelet transform , 2004, Signal Process..

[7]  Sonja Grgic,et al.  VCL@FER image quality assessment database , 2011, Proceedings ELMAR-2011.

[8]  Wilfried Philips,et al.  Efficient blur estimation using multi-scale quadrature filters , 2013, Signal Process..

[9]  Wilfried Philips,et al.  Parametric PSF estimation via sparseness maximization in the wavelet domain , 2004, SPIE Optics East.

[10]  Steven W. Zucker,et al.  Local Scale Control for Edge Detection and Blur Estimation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[12]  Weisi Lin,et al.  No-Reference Image Blur Assessment Based on Discrete Orthogonal Moments , 2016, IEEE Transactions on Cybernetics.

[13]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

[14]  Chaofeng Li,et al.  No-reference blur index using blur comparisons , 2011 .

[15]  Rafael Molina,et al.  Iterative image restoration using nonstationary priors. , 2013, Applied optics.

[16]  Sim Heng Ong,et al.  Image Analysis by Tchebichef Moments , 2001, IEEE Trans. Image Process..

[17]  Judith Dijk,et al.  Precise local blur estimation based on the first-order derivative , 2012, Defense + Commercial Sensing.

[18]  R. Venkatesh Babu,et al.  No-reference image quality assessment using modified extreme learning machine classifier , 2009, Appl. Soft Comput..

[19]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[20]  Eric C. Larson,et al.  Most apparent distortion: full-reference image quality assessment and the role of strategy , 2010, J. Electronic Imaging.

[21]  Kim-Han Thung,et al.  Content-based image quality metric using similarity measure of moment vectors , 2012, Pattern Recognit..

[22]  Houzhang Fang,et al.  Blind image deconvolution with spatially adaptive total variation regularization. , 2012, Optics letters.

[23]  Fen Chen,et al.  An Empirical Identification Method of Gaussian Blur Parameter for Image Deblurring , 2009, IEEE Transactions on Signal Processing.