Sparse Bayesian blind image deconvolution with parameter estimation

Abstract

In this article, we propose a novel blind image deconvolution method developed within the Bayesian framework. We concentrate on the restoration of blurred photographs taken by commercial cameras to show its effectiveness. The proposed method is based on a non-convex l p quasi norm with 0 < p < 1 that is used for the image, and a total variation (TV) based prior that is utilized for the blur. Bayesian inference is carried out by utilizing bounds for both the image and blur priors using a majorization-minimization principle. Maximum a posteriori estimates of the unknown image, blur and model parameters are calculated. Experimental results (i.e., restorations of more than 30 blurred photographs) are presented to demonstrate the advantage of the proposed method compared to existing ones.

Compressive Blind Image Deconvolution

“…Now, we support our claim, in section II-C, that the proposed simultaneous CS BID approach is superior to the Example restorations: 1 st column represents three different uncompressed blurred PMMW images of size 41 × 43 pixels, obtained from [31]. The PMMW images depict two cars and the middle part of a pair of scissors; 2 nd column represents the blind deconvolution result, without CS, using the algorithm in [34]; 3 rd , 4 th , and 5 th columns represent, respectively, the restorations obtained by the proposed algorithm for compressive ratios 0.8, 0.6 and 0.4, where is a binary S-cyclic matrix (see [53]- [55] for more details).…”

“…Note that the blurred-uncompressed images on the 1 st column of Figure 10 correspond to the best achievable reconstruction when the blurring function is not taken into consideration. Furthermore, for comparison purposes, we provide a blind deconvolution result, without CS, using the method presented in [34]. Figure 11 depicts the estimated PSFs, using our approach, for the reconstruction/restoration of the PMMW images in Figure 10.…”

Image Deblurring Based on Spectral Measures of Whiteness

“…Here the deblurring process leads to infinite number of solutions due to the presence of many pairs of blurring filters and image estimates. To solve this problem, most blind image deblurring methods restrict the type of blur filter based on either the use of regularizers [2], or through the use of parametric models [1], that are either through the soft way or hard way. This method aims to estimate the unknown blur from the observed blurred image and hence recover the original sharp image.…”

Improved Skin Lesion Diagnostics for General Practice by Computer-Aided Diagnostics

“…Recently, a novel blind image deconvolution algorithm [94] was developed within a Bayesian framework utilizing a non-convex quasi norm based sparse prior on the image and a total variation prior on the unknown blur.…”