A Kullback-Leibler divergence approach for wavelet-based blind image deconvolution

Seghouane, Abd‐Krim; Hanif, Muhammad

doi:10.1109/mlsp.2012.6349757

Cited by 5 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cost function considered in [27] is the Kullback-Leibler (KL) divergence [77], which is a measure of the difference between two probability distributions. Such a cost function arises in blind deconvolution when variational approach is used for estimating the PSF and the image [6,92,102,106,142,143,180]. In regularization or MAP based joint estimation the cost function is different as observed in the Chaps.…”

Section: Spatial Domain Convergence Analysismentioning

confidence: 99%

Blind Image Deconvolution

Chaudhuri

Velmurugan

Rameshan

2014

View full text Add to dashboard Cite

Section: Spatial Domain Convergence Analysismentioning

confidence: 99%

Blind Image Deconvolution

Chaudhuri

Velmurugan

Rameshan

2014

View full text Add to dashboard Cite

“…To cope with this problem some prior constraints on B or x must be employed [2,4,5]. In literature BID is mostly addressed using deconvolution based methods, where B is de-convolved with y to get a sharp version x [6]. These methods can be categorized into two groups [1]; i) disjoint blur identification and image restoration; ii) estimate blur and sharp image simultaneously in one procedure.…”

Section: Introductionmentioning

confidence: 99%

Blind image deblurring using non-negative sparse approximation

Hanif

Seghouane

2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Blurring is a common source of image degradation in many applications. Blind image deblurring (BID) is an apposite approach for blur removal in real images. Being an ill-posed linear inverse problem, a regularized and well constrained approach is required for a credible solution of BID model. Recently sparse representation base modeling emerged as an efficacious tool in image processing community, with application as regularizer in inverse problems. In this work the sparsity constraint is fused with the non-negative matrix approximation to address the BID problem. An alternative-iterative frame work is developed to estimate the non-negative sparse approximation of the sharp image and blurring kernel. With sparsity constraint, an estimate of the sharp image is obtained without solving the ill-posed deconvolution model. Although similar formulation has been proposed but unlike other BID methods the proposed approach is parameter free and requires no prior statistics. The experimental results validate comparatively better performance of proposed method against the other methods.

show abstract

“…It is quite evident now that wavelet subband coefficients of natural images have highly non-Gaussian statistics [14], represent heavy tailed distributions. The usefulness of heavy-tailed priors for natural images are already exercised in image denoising [13,15], motion deblurring [12], blind deconvolution [1,16], image restoration [17,18,19] and video matting [20]. Some example of this priors class includes the generalized Gaussian [21], the Jeffrey's noninformative prior [15], and the Gaussian mixture (GM) [17].…”

Section: Introductionmentioning

confidence: 99%

An effective image restoration using Kullback-Leibler divergence minimization

Hanif

Seghouane

2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Image restoration is a significant inverse problem in image processing community. We present an iterative alternating minimization of Kullback Leibler divergence (KLD) for an optimized image denoising. It is obtained by modeling the original image and the additive noise as multivariate Gaussian processes with unknown covariance matrices in wavelet domain. The original image and noise parameters are estimated by minimizing KLD between a model family of probability distributions defined using the linear image degradation model and a desired family of probability distributions constrained to be concentrated on the observed noisy image. The wavelet coefficients are modeled using the class of Gaussian Scale Mixture (GSM), which represents the heavy-tailed statistical distribution, suitable for natural images. The algorithm provides closed form expressions for the parameters updates and converge only in few iterations. The efficiency of proposed method is demonstrated through numerical simulations, both visually and in terms of signal to noise ratio.

show abstract

A Kullback-Leibler divergence approach for wavelet-based blind image deconvolution

Cited by 5 publications

References 19 publications

Blind Image Deconvolution

Blind Image Deconvolution

Blind image deblurring using non-negative sparse approximation

An effective image restoration using Kullback-Leibler divergence minimization

Contact Info

Product

Resources

About