Search

Motion blur is a common artifact in image processing, specifically in e-health services, which is caused by the motion of a camera or scene. In linear motion cases, the blur kernel, i.e., the function that simulates the linear motion blur process, depends on the length and direction of blur, called linear motion blur parameters. The estimation of blur parameters is a vital and sensitive stage in the process of reconstructing a sharp version of a motion blurred image, i.e., image deblurring. The estimation of blur parameters can also be used in e-health services. Since medical images may be blurry, this method can be used to estimate the blur parameters and then take an action to enhance the image. In this paper, some methods are proposed for estimating the linear motion blur parameters based on the extraction of features from the given single blurred image. The motion blur direction is estimated using the Radon transform of the spectrum of the blurred image. To estimate the motion blur length, the relation between a blur metric, called NIDCT (Noise-Immune Discrete Cosine Transform-based), and the motion blur length is applied. Experiments performed in this study showed that the NIDCT blur metric and the blur length have a monotonic relation. Indeed, an increase in blur length leads to increase in the blurriness value estimated via the NIDCT blur metric. This relation is applied to estimate the motion blur. The efficiency of the proposed method is demonstrated by performing some quantitative and qualitative experiments.

Blind image deblurring, i.e., reconstructing a sharp version of a blurred image, is generally an ill-posed problem, as both the blur kernel and the sharp image are unknown. To solve such problem, one must use effective image and blur kernel priors. In this paper, a blind image deblurring method is proposed, which uses an effective image prior based on both the first and second order gradients of the image. This prior causes to properly reconstruct salient edges which provide reliable edge information for kernel estimation in the intermediate latent image. This prior along with a hyper-Laplacian kernel prior can be used to solve the optimization problem in the form of maximum-a posteriori-problem, and hence obtaine the blur kernel with a high accuracy. The efficiency of the proposed method is demonstrated by performing several quantitative and qualitative comparisons with the state-of-the-art methods, on both a benchmark image dataset and real-world motion blurred images.

Local motion deblurring is a highly challenging problem as both the blurred region and the blur kernel are unknown. Most existing methods for local deblurring require a specialized hardware, an alpha matte, or user annotation of the blurred region. In this paper, an automatic method is proposed for local motion deblurring in which a segmentation step is performed to extract the blurred region. Then, for blind deblurring, i.e., simultaneously estimating both the blur kernel and the latent image, an optimization problem in the form of maximum-a-posteriori (MAP) is introduced. An effective image prior is used in the MAP based on both the first- and second-order gradients of the image. This prior assists to well reconstruct salient edges, providing reliable edge information for kernel estimation, in the intermediate latent image. We examined the proposed method for both global and local deblurring. The efficiency of the proposed method for global deblurring is demonstrated by performing several quantitative and qualitative comparisons with the state-of-the-art methods, on both a benchmark image dataset and real-world motion blurred images. In addition, in order to demonstrate the efficiency in local motion deblurring, the proposed method is examined to deblur some real-world locally linear motion blurred images. The qualitative results show the efficiency of the proposed method for local deblurring at various blur levels.

Image deconvolution is an ill-posed problem that requires a regularization term to solve. The most common forms of image priors used as the regularization term in image deconvolution tend to produce smoothed (slightly blurry) images, hence don’t well reconstruct image details. In this paper, a new image prior is introduced. This prior is used as a regularization term to model the non-blind image deconvolution problem. The complete regularization term consists of two parts: one that penalizes non-sparsity of the gradient, and the other that penalizes the blurriness in the image. The resulting regularization term favors sharp images over blurry ones. It means that the minimum of this term corresponds to the true sharp solution. The minimization problem is non-convex and we propose a scheme based on half-quadratic regularization. We demonstrate the efficiency of the proposed method by performing several quantitative and qualitative comparisons with the existing non-blind image deconvolution methods for deblurring artificial and real blurred images. The experimental results show that the proposed method tends to well reconstruct image details whilst suppresses noise. In addition, the reconstructed images have a higher PSNR and a lower blurriness value compared to those in the existing methods.

Blur is a type of distortion that may happen in digital images. Blur estimation is an important issue in image processing applications such as image deblurring and depth estimation. Several blur metrics exist in the literature, but they are mostly sensitive to the presence of noise. In this paper, a simple yet accurate no-reference blur metric with low computational cost is proposed, which is robust against noise. The proposed blur metric is based on the observation that there is a considerable difference between the DCT of a sharp image and the one associated with its blurred version. The effect of noise is mainly reflected in the higher order DCT coefficients. Hence, the noise effect is mitigated in this paper via discarding the higher order DCT coefficients. The experiments, performed on four databases (including CSIQ, TID2008, IVC, and LIVE), indicate the capability of the proposed metric in measuring image blurriness. Comparative results with other existing approaches show the superiority of the proposed blur metric, especially at the presence of noise.

Digital images may contain undesired blurred regions. Automatic detection of such regions and estimation of the amount of blurriness in a given image are important issues in many computer vision applications. This paper presents a simple and effective method to automatically detect blurred regions. The proposed method consists of two main parts. First, a novel blur metric, which can significantly distinguish blur and non-blur regions, is proposed. This metric is then used to generate a blur map to encode the amount of blurriness for individual pixels in a given image. Finally, the estimated blur map is used to segment the input image into blurred/non-blurred regions by applying a pixon-based technique. The proposed approach is evaluated for out-of-focus and motion-blurred natural images. By conducting experiments on a large dataset containing real images with defocus blur and partial motion blur regions, qualitative and quantitative measures are performed. The obtained results in this paper show that the proposed approach outperforms the state-of-the-art methods for blur estimation in digital images.

Motion blur is a common blur type that created due to motion of camera or some objects in scene. The blur kernel, i.e. the function that simulate the motion blur process, depends on the length of blur. Therefore, the estimation of blur length is a vital and sensitive stage in the process of reconstructing a sharp version of a motion blurred image, i.e. image deblurring. In this paper, a method is proposed for estimation of the motion blur length using the evolutionary methods. To do this, we take the advantage of the relation between a blur metric, called NIDCT, and the blur length. Then this relation is learned via the evolutionary algorithms. The learned relation can be used to estimate the motion blur length in a blurred image. The efficiency of the proposed method is demonstrated by performing some quantitative and qualitative experiments.