Search

Image restoration with impulse noise is an important task in image processing. Taking into account the statistical distribution of impulse noise, the ℓ1‐norm data fidelity and total variation (ℓ1TV$\ell _1TV$) model has been widely used in this area. However, the ℓ1TV$\ell _1TV$ model usually performs worse when the noise level is high. To overcome this drawback, several nonconvex models have been proposed. In this paper, an efficient iterative algorithm is proposed to solve nonconvex models arising in impulse noise. Compared to existing algorithms, the proposed algorithm is a completely explicit algorithm in which every subproblem has a closed‐form solution. The key idea is to transform the original nonconvex models into an equivalent constrained minimization problem with two separable objective functions, where one is differentiable but nonconvex. As a consequence, the proximal linearized alternating direction method of multipliers is employed to solve it. Extensive numerical experiments are presented to demonstrate the efficiency and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Image restoration is an interesting ill-posed problem. It plays a critical role in the concept of image processing. We are looking for an image that is as near to the original as possible among images that have been skewed by Gaussian and additive noise. Image deconstruction is a technique for restoring a noisy image after it has been captured. The numerical results achieved by the prox-penalty method and the split Bregman algorithm for anisotropic and isotropic TV denoising problems in terms of image quality, convergence, and signal noise rate (SNR) are compared in this paper. It should be mentioned that isotropic TV denoising is faster than anisotropic. Experimental results indicate that the prox algorithm produces the best high-quality output (clean, not smooth, and textures are preserved). In particular, we obtained (21.4, 21) the SNR of the denoising image by the prox for sigma 0.08 and 0.501, such as we obtained (10.0884, 10.1155) the SNR of the denoising image by the anisotropic TV and the isotropic TV for sigma 0.08 and (-1.4635, -1.4733) for sigma 0.501. [ABSTRACT FROM AUTHOR]

In this paper, a variable projection approach based on the BFGS (Broyden–Fletcher–Goldfarb–Shanno) method for image reconstruction problems is proposed, which is an alternative to the common alternating minimisation scheme. The image restoration is expressed as a nonlinear least‐squares problem with reduced parameter space. To improve the efficiency of the algorithm, the BFGS method is proposed to be used to optimise the reduced objective function. The large‐scale problem considered in this paper is projected on to a small Krylov subspace using Lanczos bidiagonalisation. The regularisation parameter is selected by a weighted generalised cross validation criterion. Numerical examples demonstrate the efficiency and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Fractional-order derivative is attracting more and more attention of researchers in image processing because of its better property in restoring more texture than the total variation. To improve the performance of fractional-order variation model in image restoration, a truncated fractional-order variation model was proposed in Chan and Liang [Truncated fractional-order variation model for image restoration, J. Oper. Res. Soc. China]. In this paper, we propose a dual approach to solve this truncated fractional-order variation model on noise removal. The proposed algorithm is based on the dual approach proposed by Chambolle [An algorithm for total variation minimisation and applications, J. Math Imaging Vis. 20 (2004), pp. 89–97]. Conversely, the Chambolle's dual approach can be treated as a special case of the proposed algorithm with fractional order α = 1. The work of this paper modifies the result in Zhang et al. [Adaptive fractional-order multi-scale method for image denoising, J. Math. Imaging Vis. 43(1) (2012), pp. 39–49. Springer Netherlands 0924–9907, Computer Science, pp. 1–11, 2011], where the convergence is not analysed. Based on the truncation, the convergence of the proposed dual method can be analysed and the convergence criteria can be provided. In addition, the accuracy of the reconstruction is improved after the truncation is taken. [ABSTRACT FROM AUTHOR]

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. [ABSTRACT FROM AUTHOR]

The majority of medical workers are eager to obtain realistic and real-time CT 3D reconstruction results. However, autonomous or involuntary motion of patients can cause blurring of CT images. For the 3D reconstruction scene of motion-blurred CT image, this paper consists of two parts: firstly, a GAN image translation network deblurring algorithm is proposed to remove blurred results. This algorithm adopts the clear image to supervise the training process of the blurred image, which creates solutions that are close to the clear image. Secondly, this paper proposes a Marching Cubes (MC) algorithm based on the fusion of golden section and isosurface direction smooth (GI-MC) for 3D reconstruction of CT images. The golden section algorithm is used to calculate the equivalent points and normal vectors, which reduces the calculation numbers from four to one. The isosurface direction smooth algorithm computes the mean value of the normal vector, so as to smooth the direction of all triangular patches in spatial arrangement. The experimental results show that for different blurred angle and blurred amplitude, comparing the results of the Shannon entropy ratio and peak signal-to-noise ratio, our GAN image translation network deblurring algorithm has better restoration than other algorithms. Furthermore, for different types of liver patients, the reconstruction accuracy of our GI-MC algorithm is 9.9%, 7.7%, and 3.9% higher than that of the traditional MC algorithm, Li's algorithm, and Pratomo's algorithm, respectively. [ABSTRACT FROM AUTHOR]

The increase in computational power in recent years has opened a new door for image processing techniques. Three-dimensional object recognition, identification, pose estimation, and mapping are becoming popular. The need for real-world objects to be mapped into three-dimensional spatial representation is greatly increasing, especially considering the heap jump we obtained in the past decade in virtual reality and augmented reality. This paper discusses an algorithm to convert an array of captured images into estimated 3D coordinates of their external mappings. Elementary methods for generating three-dimensional models are also discussed. This framework will help the community in estimating three-dimensional coordinates of a convex-shaped object from a series of two-dimension images. The built model could be further processed for increasing the resemblance of the input object in terms of its shapes, contour, and texture. [ABSTRACT FROM AUTHOR]

The increase in computational power in recent years has opened a new door for image processing techniques. Three-dimensional object recognition, identification, pose estimation, and mapping are becoming popular. The need for real-world objects to be mapped into three-dimensional spatial representation is greatly increasing, especially considering the heap jump we obtained in the past decade in virtual reality and augmented reality. This paper discusses an algorithm to convert an array of captured images into estimated 3D coordinates of their external mappings. Elementary methods for generating three-dimensional models are also discussed. This framework will help the community in estimating three-dimensional coordinates of a convex-shaped object from a series of two-dimension images. The built model could be further processed for increasing the resemblance of the input object in terms of its shapes, contour, and texture. [ABSTRACT FROM AUTHOR]

Color demosaicing is an essential step in the camera image processing pipeline, especially on hardware platforms for real-time video applications. Though many demosaicing algorithms have been proposed in the past two decades, there remains a substantial gap between industrial needs and academic research. On one hand, industry requires a high perceptual quality, artifact-free, and low-cost demosaicing algorithm that is noniterative and small window based ready to be implemented on a hardware platform with a limited line buffer. On the other hand, academia is targeting high PSNR/SSIM, with the computation cost and line buffer receiving second priority, and often a frame buffer and iterative operation are used. The cost, large line buffer and iteration requirement make most existing demosaicing algorithms inapplicable on hardware platforms. In this paper, we introduce a novel low-cost demosaicing algorithm to narrow the gap. We keep the operation window size and computation cost as the first priority and achieve both high PSNR/SSIM and visual perceptual quality compared to previous state-of-the-art methods on standard test datasets. We fully investigate the a priori knowledge of natural scene raw images and find several key cues that are beneficial to demosaicing. Our demosaicing algorithm is a smart fusion of these useful cues. Furthermore, we solve typical demosaicing issues that occur in many traditional methods, including false color artifacts, T-section closing, and zippering artifacts. The proposed method has no learning stage, no iteration operation, a small line buffer and a limited number of parameters, so it can easily be applied to hardware platforms. [ABSTRACT FROM AUTHOR]

In the process of image shooting, image stabilization is an inevitable problem. Therefore, this paper finds an efficient and simple image stabilization algorithm in image stabilization. Using a new image regularization method to reduce the cost of real and clear images, and apply it to the blind deconvolution model without any additional cost. Because of its rapidity and robustness, it matches the processing performance of DSP in image processing. In this article, after re-encoding, so that it can be applied to the DSP, and thus enhance the processing speed of the image processing. In addition, because of the portability of DSP, the DSP embedded with the algorithm can be transplanted to the UAV. The fuzzy picture produced after the shooting is processed in real time to reduce the workload of the later picture processing. Experiments show that the scheme proposed in this paper can achieve real-time performance under the precondition of guaranteeing the computing effect, so as to improve the operating efficiency of the whole system. [ABSTRACT FROM AUTHOR]

Due to the ill-posed nature of image restoration, seeking a meaningful image prior is still a great challenge in the field of image processing. The total variation with overlapping group sparsity (OGS-TV) has been successfully applied for image denoising/deblurring. In this paper, we further study the overlapping group sparsity of the image gradient. The sparsity is measured by the ℓ q quasi-norm (0 < q < 1). The proposed regularizer comes down to the well-known hyper-Laplacian prior if the overlapping group size is 1. Although it seems to be a simple extensive study compared with the previous works, its regularization capability and corresponding mathematical problems are still in demand for imaging science. To solve the non-convex and non-smooth minimization problem, we use the alternating direction method of multipliers as the main algorithm framework. The difficult inner subproblem is tackled by the majorization-minimization method with the sophisticatedly derived majorizer. We carry out some numerical experiments to demonstrate the effectiveness of the proposed regularizer in terms of PSNR and SSIM values. [ABSTRACT FROM AUTHOR]

This paper proposes a robust deblurring algorithm for noisy images with just noticeable blur (JNB). Natural images are usually accompanied by JNB and noise when viewed under pixel scale resolution, but are easily neglected. In this paper, we describe the JNB phenomenon and briefly analyze its causes. An image-gradient-related constrained factor is introduced in our algorithm based on the prior of image noise’s low gradient distribution. Richardson-Lucy method is also adopted to reduce algorithm’s time cost. For large-size cellphone images, we put forward an effective image segmentation model suitable for space-variant blur. Experiments show that our method obtains high-quality deblurring images and are competitive to state-of-the-art deblurring algorithms. [ABSTRACT FROM AUTHOR]

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks (NNs) and cascaded NNs have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the application of the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by strictly separating the application of the NN, the regularization of the solution and the consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained NN which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative NNs. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude. [ABSTRACT FROM AUTHOR]

Dictionary learning has emerged as a powerful tool for a range of image processing applications and a proper dictionary always plays a key issue to the final achievable performance. In this paper, a class-oriented discriminative dictionary learning (CODDL) method is presented for image classification applications. It takes a comprehensive consideration of multiple optimization objectives, emphasizing class discrimination of both dictionary atoms and representation coefficients. The atoms of the learned dictionary should be grouped into class level sub-dictionaries. Meanwhile, the sparse representation coefficients of an input sample should be concentrated on the sub-dictionary of the class it belongs to. Then, based on the learned class-oriented discriminative dictionary, the structured representation coefficients can thus be used for image classification with a simple and efficient classification scheme. The superior performance of the proposed algorithm is demonstrated through extensive experiments. [ABSTRACT FROM AUTHOR]

Restoring images corrupted by Poisson noise have attracted much attention in recent years due to its significant applications in image processing. There are various regularization methods of solving this problem and one of the most famous is the total variation (TV) model. In this paper, we present a new method based on accelerated alternating minimization algorithm (AAMA) which involves minimizing the sum of a Kullback–Leibler divergence term and a TV term for restoring Poisson noise degraded images. Our proposed algorithm is applied in solving the aforementioned problem and its convergence analysis is established under very weak conditions. In addition, the numerical examples reported demonstrate the efficiency and versatility of our method compared to existing methods of restoring images with Poisson noise. [ABSTRACT FROM AUTHOR]

Abstract The electrical capacitance tomography (ECT) technology is a promising tomography technology that can image the distribution information of permittivity in a measurement region. The imaging algorithms play crucial roles in practical ECT image reconstruction problems. Different from previous numerical methods, this study proposes a novel cost function to model the ECT inverse problem, in which the L1-norm is used as the data fidelity to weaken the influence of the outliers contained in the capacitance data, the L1 regularization is introduced to enhance the sparseness of reconstructed objects, and the second order total variation (STV) regularization is used to weaken the staircasing effects caused by the first order total variation (FTV) regularization. The split Bregman iteration (SBI) algorithm that splits a complicated ECT imaging problem into several simpler sub-problems is developed to solve the proposed cost function effectively. The numerical simulation results show that the imaging algorithm proposed in this paper can reconstruct satisfactory results. Highlights • A new cost function is proposed to model the ECT imaging problem. • A new iterative algorithm is developed to effectively solve the cost function. • The feasibility and effectiveness of the algorithm are numerically validated. [ABSTRACT FROM AUTHOR]

In order to retrieve similar trademarks from large-scale trademark databases, combining the characteristics of trademark images, this paper presents a trademark image retrieval method based on regional and border feature fusion. Based on the target image extraction, the proposed approach describes the target region and border features. The region feature description is mainly based on the concept of partition block statistics. The region is divided into equal-area unit using concentric circles, and feature extraction is performed in each small block unit. For the border feature description, this study first detect corners, and then construct a Delaunay graph and extract features by combining the corner detected and the Delaunay triangulation reconstruction. In the search process, the method also incorporates information such as the trademark's color characteristics, trademark classification, and trademark keywords. The present study carried out image retrieval experiment on CE-SHAPE-1 database containing 1400 MPEG-7 core experimental shape, a classification trademark database containing 2000 images, and a national trademark database containing approximately 4.89 million images. The experimental results show that the proposed approach combines the advantages of region and border feature description, and can choose the best among various local optimizations, which makes the retrieval result more effective, more in line with human visual perception, and improves the retrieval accuracy. [ABSTRACT FROM AUTHOR]

The automatic reconstruction of single neurons from microscopic images is essential to enable large-scale data-driven investigations in neuron morphology research. However, few previous methods were able to generate satisfactory results automatically from 3-D microscopic images without human intervention. In this paper, we developed a new algorithm for automatic 3-D neuron reconstruction. The main idea of the proposed algorithm is to iteratively track backward from the potential neuronal termini to the soma centre. An online confidence score is computed to decide if a tracing iteration should be stopped and discarded from the final reconstruction. The performance improvements comparing with the previous methods are mainly introduced by a more accurate estimation of the traced area and the confidence controlled back-tracking algorithm. The proposed algorithm supports large-scale batch-processing by requiring only one user specified parameter for background segmentation. We bench tested the proposed algorithm on the images obtained from both the DIADEM challenge and the BigNeuron challenge. Our proposed algorithm achieved the state-of-the-art results. [ABSTRACT FROM AUTHOR]

The objective of superresolution is to reconstruct a high-resolution image by using the information of a set of low-resolution images. Recently, the variational Bayesian superresolution approach has been widely used. However, these methods cannot preserve edges well while removing noises. For this reason, we propose a new image prior model and establish a Bayesian superresolution reconstruction algorithm. In the proposed prior model, the degree of interaction between pixels is adjusted adaptively by an adaptive norm, which is derived based on the local image features. Moreover, in this paper, a monotonically decreasing function is used to calculate and update the single parameter, which is used to control the severity of penalizing image gradients in the proposed prior model. Thus, the proposed prior model is adaptive to the local image features thoroughly. With the proposed prior model, the edge details are preserved and noises are reduced simultaneously. A variational Bayesian inference is employed in this paper, and the formulas for calculating all the variables including the HR image, motion parameters, and hyperparameters are derived. These variables are refined progressively in an iterative manner. Experimental results show that the proposed SR approach is very efficient when compared to existing approaches. [ABSTRACT FROM AUTHOR]

Minimization functionals related to Euler’s elastica energy has a broad range of applications in computer vision and image processing. This paper proposes a novel Euler’s elastica and curvature-based variational model for image restoration corrupted with multiplicative noise. It combines Euler’s elastica curvature with a Weberized total variation (TV) regularization and gets a novel Euler’s elastica energy and TV-based minimization functional. The combined approach in this variational model can preserve edges while reducing the blocky effect in smooth regions. The implicit gradient descent scheme is applied to efficiently finding the minimizer of the proposed functional. Experimental results demonstrate the effectiveness of the proposed model in visual improvement, as well as an increase in the peak signal-to-noise ratio, compared to the PDE-based methods. [ABSTRACT FROM AUTHOR]

The example-based super-resolution (SR) methods can be mainly categorized into two classes: the internal SR methods and the external SR methods. The internal SR methods only use samples obtained from a single low resolution (LR) input, while the external SR methods only utilize an external database. The complementary information included in internal and external samples is rarely taken into account. This paper presents a novel extraction and learning method about the complementary information between external samples and internal samples, and then the learned complementary information is used to improve the single image SR performance. Firstly, we construct an initial high resolution (HR) image via sparse coding over the learned dictionary pair with external samples. Secondly, we propose an adaptive sample selection scheme (ASSS) to acquire the mixed samples. Thirdly, we present a novel adaptive mixed samples ridge regression (AMSRR) model to effectively learn the complementary information included in the mixed samples. Finally, we optimize the SR image. Extensive experimental results validate the effectiveness of the proposed algorithm comparing with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

High dynamic range (HDR) imaging has gained great popularity over the past twenty years. Tone mapping operator (TMO) is the key component that enables reproduction of HDR images on the standard low dynamic range (LDR) display devices. When it comes to the HDR video, design of the TMO becomes especially challenging since temporal control of TMO parameters is needed in order to avoid possible artifacts. Since temporal and spatial contrast cannot be met simultaneously, existing solutions are usually designed to optimize one of these two requirements. We present novel local tone mapping operator that preserves details and simultaneously provides good local and global contrast of processed images. Tunable temporal control enables trade-off between spatial and temporal contrast of a tone mapped video. Flexible control presented in this paper ensures that both requirements can be met with a single operator just by using different tuning of the control block.When compared to the state-of-the-art TMOs, proposed solution exhibits better results regarding overall image quality. [ABSTRACT FROM AUTHOR]

Single image super-resolution (SR) aims at generating a plausible and visually pleasing high-resolution (HR) image from a low-resolution (LR) input. In this paper, we propose an effective single image SR algorithm by using collaborative representation and exploiting non-local self-similarity of natural images. In particular, the collaborative-representation-based method is applied to build the so-called self-projection matrices from a training set of HR images. Then the learned self-projection matrices are used to establish the collaborative-representation-based regularization (CRR), which is responsible for introducing the external HR information. Furthermore, to guarantee a reliable estimation of the HR image, the non-local low-rank regularization (NLR) which exploits internal prior of images is also taken into consideration. Since the CRR term and NLR term are complementary, they are assembled together to form a new reconstruction-based framework for SR recovery. Finally, to implement the proposed framework, an iterative algorithm is designed to gradually improve the quality of the SR results. Extensive experimental results indicate that the proposed approach is capable of delivering higher quality of SR results than several state-of-the-art SR methods. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) is the theory and practice of sub-Nyquist sampling of sparse signals of interest. Exact reconstruction may then be possible with much fewer than the Nyquist-required number of data. In this paper, we consider a multiview video system in which multiple cameras at different locations perform independent CS to simultaneously capture different views of a scene. At the decoder, we propose a disparity- and motion-compensated total variation minimization algorithm to jointly reconstruct the multiview video sequence. The experimental results show that the proposed joint reconstruction algorithm successfully exploits simultaneously intra-frame, inter-frame, and inter-view sparsity and significantly outperforms existing independent-view reconstruction, residue-view reconstruction, and motion-adaptive reconstruction algorithms. [ABSTRACT FROM AUTHOR]

Image reconstruction from discrete electrical responses pose a number of computational and mathematical challenges. Application of smoothness constrained regularized inversion from limited measurements may fail to detect resistivity anomalies and sharp interfaces separated by hydro stratigraphic units. Under favourable conditions, compressed sensing (CS) can be thought of an alternative to reconstruct the image features by finding sparse solutions to highly underdetermined linear systems. This paper deals with the development of a CS assisted, 3-D resistivity inversion algorithm for use with hydrogeologists and groundwater scientists. CS based l 1 -regularized least square algorithm was applied to solve the resistivity inversion problem. Sparseness in the model update vector is introduced through block oriented discrete cosine transformation, with recovery of the signal achieved through convex optimization. The equivalent quadratic program was solved using primal-dual interior point method. Applicability of the proposed algorithm was demonstrated using synthetic and field examples drawn from hydrogeology. The proposed algorithm has outperformed the conventional (smoothness constrained) least square method in recovering the model parameters with much fewer data, yet preserving the sharp resistivity fronts separated by geologic layers. Resistivity anomalies represented by discrete homogeneous blocks embedded in contrasting geologic layers were better imaged using the proposed algorithm. In comparison to conventional algorithm, CS has resulted in an efficient (an increase in R 2 from 0.62 to 0.78; a decrease in RMSE from 125.14 Ω-m to 72.46 Ω-m), reliable, and fast converging (run time decreased by about 25%) solution. [ABSTRACT FROM AUTHOR]

With advantages of portability, low-cost and noninvasive detection, electrical impedance tomography (EIT) has great potential application value as a bedside monitor. Because image reconstruction in EIT involves addressing serious ill-posed inverse problems, realizing EIT online dynamic display still remains a challenging work. In this paper, an EIT imaging system with the function of online dynamic display was designed. Split augmented Lagrangian shrinkage algorithm (SALSA), which transforms an unconstrained optimization EIT inverse problem into an equivalent constrained optimization problem, was adopted in the proposed system. On the basis of EIT imaging simulation, a high-precise Compact PCI-based EIT system was implemented with FPGA. And experiments of EIT cylinder imaging and in-vivo monitoring were conducted to verify the feasibility of the system. The results indicated that the online dynamic display frame rate of the system, which was centered with a computer (Intel i7 2.2 GHz, 4 GB RAM), was up to 32 fps. [ABSTRACT FROM AUTHOR]

This paper is an in-depth look at the problem of removing the blur from a complex motion-blurred star image. Accordingly, a simple yet effective l p ( 0 < p ≤ 1 ) -regularized deblurring method based on stars image intensity is proposed. The model builds on the principle that the intensity of clear star image is in accordance with Laplacian distribution or generalized p Gaussian distribution. Further, two algorithms are introduced to solve the ensuing non-smooth ( p = 1 ) or non-convex ( p < 1 ) constrained optimization problem. Simulations and actual star image restoration experiment are implemented to demonstrate that the centroids extraction accuracy of the proposed method is higher than 0.1 pixel, the running time is 3 to 5 times better than Richardson–Lucy filter or other methods based on image gradient constraint, and the peak signal to noise ratio (PSNR) of recovered star images excel results of several other image deconvolution methods. [ABSTRACT FROM AUTHOR]

Abstract: The problem of image reconstruction from its statistical moments is particularly interesting to researchers in the domain of image processing and pattern recognition. Compared to geometric moments, the orthogonal moments offer the ability to recover much more easily the image due to their orthogonality, which allows reducing greatly the complexity of computation in the phase of reconstruction. Since the 1980s, various orthogonal moments, such as Legendre moments, Zernike moments and discrete Tchebichef moments have been introduced early or late to image reconstruction. In this paper, another set of orthonormal moments, the Gaussian–Hermite moments, based on Hermite polynomials modulated by a Gaussian envelope, is proposed to be used for image reconstruction. Especially, the paper''s focus is on the determination of the optimal scale parameter and the improvement of the reconstruction result by a post-processing which make Gaussian–Hermite moments be useful and comparable with other moments for image reconstruction. The algorithms for computing the values of the basis functions, moment computation and image reconstruction are also given in the paper, as well as a brief discussion on the computational complexity. The experimental results and error analysis by comparison with other moments show a good performance of this new approach. [Copyright &y& Elsevier]

Abstract: Orthogonal moments are powerful tools in pattern recognition and image processing applications. In this paper, the Gaussian–Hermite moments based on a set of orthonormal weighted Hermite polynomials are extensively studied. The rotation and translation invariants of Gaussian–Hermite moments are derived algebraically. It is proved that the construction forms of geometric moment invariants are valid for building the Gaussian–Hermite moment invariants. The paper also discusses the computational aspects of Gaussian–Hermite moment, including the recurrence relation and symmetrical property. Just as the other orthogonal moments, an image can be easily reconstructed from its Gaussian–Hermite moments thanks to the orthogonality of the basis functions. Some reconstruction tests with binary and gray-level images (without and with noise) were performed and the obtained results show that the reconstruction quality from Gaussian–Hermite moments is better than that from known Legendre, discrete Tchebichef and Krawtchouk moments. This means Gaussian–Hermite moment has higher image representation ability. The peculiarity of image reconstruction algorithm from Gaussian–Hermite moments is also discussed in the paper. The paper offers an example of classification using Gaussian–Hermite moment invariants as pattern feature and the result demonstrates that Gaussian–Hermite moment invariants perform significantly better than Hu''s moment invariants under both noise-free and noisy conditions. [Copyright &y& Elsevier]

Abstract: 3D reconstruction is a major problem in computer vision. This paper considers the problem of reconstructing 3D structures, given a 2D video sequence. This problem is challenging since it is difficult to identify the trajectory of each object point/pixel over time. Traditional stereo 3D reconstruction methods and volumetric 3D reconstruction methods suffer from the blank wall problem, and the estimated dense depth map is not smooth, resulting in loss of actual geometric structures such as planes. To retain geometric structures embedded in the 3D scene, this paper proposes a novel surface fitting approach for 3D dense reconstruction. Specifically, we develop an expanded deterministic annealing algorithm to decompose 3D point cloud to multiple geometric structures, and estimate the parameters of each geometric structure. In this paper, we only consider plane structure, but our methodology can be extended to other parametric geometric structures such as spheres, cylinders, and cones. The experimental results show that the new approach is able to segment 3D point cloud into appropriate geometric structures and generate accurate 3D dense depth map. [Copyright &y& Elsevier]

Abstract: Human hand shape features extraction from image frame sequences is one of the key steps in human hand 2D/3D tracking system and human hand shape recognition system. In order to satisfy the need of human hand tracking in real time, a fast and accurate method for acquirement of edge features from human hand images without consideration of hand over face is put forward in this paper. The proposed approach is composed of two steps, the coarse location phase (CLP) and the refined location phase (RLP) from coarseness to refinement. In the phase of CLP, the hand contour is approximately described by a polygon with concave and convex, an approach to obtaining hand shape polygon using locating points and locating lines is meticulously discussed. Then, a coarse location (CL) algorithm for extraction of interested hand shape features, such as contour, fingertips, roots of fingers, joints and the intersection of knuckle on different fingers, is proposed. In the phase of RLP, a multi-scale approach is introduced into our study to refine the features obtained by the CL algorithm. By means of defining the response strength of different types of features, a refined location (RL) algorithm is proposed. The major contribution of this paper is that the novel detection operators for features of hand images are presented in the above two steps, which have been successfully applied to our 3D hand shape tracking system and 2D hand shape recognition system. A number of comparative studies with real images and online videos demonstrate that the proposed method can extract the three defined human hand image features with high accuracy and high speed. [ABSTRACT FROM AUTHOR]

Abstract: This paper concerns color image restoration aiming at objective quality improvement of compressed color images in general rather than merely artifact reduction. In compressed color images, colors are usually represented by luminance and chrominance components. Considering characteristics of human vision system, chrominance components are generally represented more coarsely than luminance component. To recover such chrominance components, we previously proposed a model-based chrominance restoration algorithm where color images are modeled by a Markov random field. This paper presents a color image restoration algorithm derived by the MAP estimation, where all components are totally estimated. Experimental results show that the proposed restoration algorithm is more effective than the previous one. [Copyright &y& Elsevier]

In this paper, we consider denoising of image sequences that are corrupted by zero-mean additive white Gaussian noise. Relative to single image denoising techniques, denoising of sequences aims to also utilize the temporal dimension. This assists in getting both faster algorithms and better output quality. This paper focuses on utilizing sparse and redundant representations for image sequence denoising, extending the work reported in [1], [2]. In the single image setting, the K-SVD algorithm is used to train a sparsifying dictionary for the corrupted image. This paper generalizes the above algorithm by offering several extensions: i) the atoms used are 3-D; ii) the dictionary is propagated from one frame to the next, reducing the number of required iterations; and iii) averaging is done on patches in both spatial and temporal neighboring locations. These modifications lead to substantial benefits in complexity and denoising performance, compared to simply running the single image algorithm sequentially. The algorithm's performance is experimentally compared to several state-of-the-art algorithms, demonstrating comparable or favorable results. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of reconstructing an object surface from silhouettes. Previous works by other authors have shown that, based on the principle of duality, surface points can be recovered, theoretically, as the dual to the tangent plane space of the object. In practice, however, the identification of tangent basis in the tangent plane space is not trivial given a set of discretely sampled data. This problem is further complicated by the existence of bitangents to the object surface. The key contribution of this paper is the introduction of epipolar parameterization in identifying a well-defined local tangent basis. This extends the applicability of existing dual space reconstruction methods to fairly complicated shapes without making any explicit assumption on the object topology. We verify our approach with both synthetic and real-world data and compare it both qualitatively and quantitatively with other popular reconstruction algorithms. Experimental results demonstrate that our proposed approach produces more accurate estimation while maintaining reasonable robustness toward shapes with complex topologies. [ABSTRACT FROM AUTHOR]

Standard formulations of image/signal deconvolution under wavelet-based priors/regularizers lead to very high-dimensional optimization problems involving the following difficulties: the non-Gaussian (heavy-tailed) wavelet priors lead to objective functions which are nonquadratic, usually nondifferentiable, and sometimes even nonconvex; the presence of the convolution operator destroys the separability which underlies the simplicity of wavelet-based denoising. This paper presents a unified view of several recently proposed algorithms for handling this class of optimization problems, placing them in a common majorization-minimization (MM) framework. One of the classes of algorithms considered (when using quadratic bounds on non- differentiable log-priors) shares the infamous "singularity issue" (SI) of "iteratively reweighted least squares" (IRLS) algorithms: the possibility of having to handle infinite weights, which may cause both numerical and convergence issues. In this paper, we prove several new results which strongly support the claim that the SI does not compromise the usefulness of this class of algorithms. Exploiting the unified MM perspective, we introduce a new algorithm, resulting from using £1 bounds for nonconvex regularizers; the experiments confirm the superior performance of this method, when compared to the one based on quadratic majorization. Finally, an experimental comparison of the several algorithms, reveals their relative merits for different standard types of scenarios. [ABSTRACT FROM AUTHOR]

Radial basis functions are a popular basis for interpolating scattered data during the image reconstruction process in graphic analysis. In this context, the solution of a linear system of equations represents the most time-consuming operation. In this paper an efficient preconditioning technique is proposed to solve these linear systems of equations. This algorithm consists of an iterative method which enforces at each iteration a projection of the residual onto a suitable subspace called coarse space. This constraint is ensured by solving an auxiliary problem at each iteration without regularisation. As increasing the number of the coarse space basis functions increases the computational cost of the algorithm, correct selection of coarse space basis is addressed in the paper. Numerical results illustrate the convergence properties of the proposed method with wavelet-like basis functions and regular distributed radial basis functions for image reconstruction. [Copyright &y& Elsevier]

To deal with the problem of restoring degraded images with non-Gaussian noise, this paper proposes a novel cooperative neural fusion regularization (CNFR) algorithm for image restoration. Compared with conventional regularization algorithms for image restoration, the proposed CNFR algorithm can relax need of the optimal regularization parameter to be estimated. Furthermore, to enhance the quality of restored images, this paper presents a cooperative neural fusion (CNF) algorithm for image fusion. Compared with existing signal-level image fusion algorithms, the proposed CNF algorithm can greatly reduce the loss of contrast information under blind Gaussian noise environments. The performance analysis shows that the proposed two neural fusion algorithms can converge globally to the robust and optimal image estimate. Simulation results confirm that in different noise environments, the proposed two neural fusion algorithms can obtain a better image estimate than several well known image restoration and image fusion methods. [ABSTRACT FROM AUTHOR]

Abstract: Zernike moments which are superior to geometric moments because of their special properties of image reconstruction and immunity to noise, suffer from several discretization errors. These errors lead to poor quality of reconstructed image and wide variations in the numerical values of the moments. The predominant factor, as observed in this paper, is due to the discrete integer implementation of the steps involved in moment calculation. It is shown in this paper that by modifying the algorithms to include discrete float implementation, the quality of the reconstructed image improves significantly and the first-order moment becomes zero. Low-order Zernike moments have been found to be stable under linear transformations while the high-order moments have large variations. The large variations in high-order moments, however, do not greatly affect the quality of the reconstructed image, implying that they should be ignored when numerical values of moments are used as features. The 11 functions based on geometric moments have also been found to be stable under linear transformations and thus these can be used as features. Pixel level analysis of the images has been carried out to strengthen the results. [Copyright &y& Elsevier]

Abstract: Super-resolution image reconstruction produces a high-resolution image from a set of shifted, blurred, and decimated versions thereof. Previously published papers have not addressed the computational complexity of this ill-conditioned large scale problem adequately. In this paper, the computational complexity of MAP-based multiframe super-resolution algorithms is studied, and a new fast algorithm, as well as methods for parallel image reconstruction is also presented. The proposed fast algorithm splits the multiple input low-resolution images into several subsets according to their translation relations, and then applies normal MAP algorithm to each subset, the reconstructed images are processed subsequently at a successive level until the desired resolution is achieved. Experiment results are also provided to demonstrate the efficiency of the proposed techniques. [Copyright &y& Elsevier]

This paper presents a new method of compressing the dynamic range of wide dynamic range scenes. This method is based on the Multi Scale Retinex algorithm. It improves the results of the original Multi Scale Retinex algorithm in a way that retains the global brightness contrast and the natural impression of the resulting image by recombining the original picture in a certain weight. Further improvement of the global brightness contrast is achieved by adjusting the histogram of the resulting picture. The paper explores the performance of this modified algorithm on different wide dynamic range scenes and points out its advantages over other dynamic range compression algorithms. [ABSTRACT FROM AUTHOR]

• The proposed Anti-Gravity Stem-Seeking (AGSS) root image restoration algorithm can quickly and effectively repair root images. • AGSS root image restoration algorithm has good universality and does not need training data and high-performance hardware platforms. • Drought and waterlogging resistances of maizes can be effectively evaluated by the phenotypic parameters of repaired seed roots. Root phenotype detection is key to cultivating seeds with excellent traits, and requires a complete root image. However, soil occlusion, uneven lighting, and other factors cause broken points and segments in the root image. To solve this problem, an anti-gravity stem-seeking (AGSS) root image restoration algorithm is proposed in this paper to repair root images and extract root phenotype information for different resistant maize seeds. First, the obtained root image was processed using uniform illumination, grayscale, binarization, and morphological filtering to separate it from the background. Subsequently, a root skeleton map was generated using a thinning algorithm for pixel-level image processing, and the Taproot junction G was obtained. Subsequently, root pixel coordinates were obtained by traversing the root skeleton map. All root-segment endpoint coordinates were obtained using the endpoint judgment rule and stored in the endpoint list. The lateral and primary root endpoints were separated based on the lateral root judgment rule, and stored in the side root and primary root endpoint lists, respectively. Subsequently, the primary root endpoints were processed and fitted in the order short to long using arbitrary-two-endpoint spacing until all breakpoints of the primary root were found. The coordinates of the top endpoints of each principal root were obtained. Finally, the top endpoint was connected to point G based on the Bezier curve-fitting method to achieve complete root repair. The proposed AGSS root image restoration algorithm was applied to detect the root systems of maize with different resistances and wheat to evaluate its performance against the standard dataset. The results indicated a detection accuracy of greater than 90% for root taproot length and diameter. It was also found that maize drought resistance was positively correlated with root length and diameter, but negatively with the lateral root number. In contrast, the waterlogging and salt resistance traits of maize were positively correlated with the number of lateral roots. In conclusion, the proposed AGSS root image restoration algorithm can quickly and effectively repair root images, is suitable for different resistance evaluations of maize seeds, and is conducive to the detection of root phenotypes. Compared with deep learning methods, this algorithm displays advantages of fast repair, low hardware platform requirements, and less requirement of training images. The algorithm is highly suitable for deploying in small embedded systems, with broad application prospects. [ABSTRACT FROM AUTHOR]

Compressive sensing (CS) theory asserts that we can reconstruct signals and images with only a small number of samples or measurements. Recent works exploiting the nonlocal similarity have led to better results in various CS studies. To better exploit the nonlocal similarity, in this paper, we propose a non-convex smoothed rank function based model for CS image reconstruction. We also propose an efficient alternating minimization method to solve the proposed model, which reduces a difficult and coupled problem to two tractable subproblems. Experimental results have shown that the proposed method performs better than several existing state-of-the-art CS methods for image reconstruction. [ABSTRACT FROM AUTHOR]

Dictionary-based super-resolution (SR) algorithms usually select dictionary atoms based on the distance or similarity metrics. Although the optimal selection of the nearest neighbors is of central importance for such methods, the impact of using proper metrics for SR has been overlooked in literature, mainly due to the vast usage of Euclidean distance. In this paper, we present a very fast regression-based algorithm, which builds on the densely populated anchored neighborhoods and sublinear search structures. We perform a study of the nature of the features commonly used for SR, observing that those features usually lie in the unitary hypersphere, where every point has a diametrically opposite one, i.e., its antipode, with same module and angle, but the opposite direction. Even though, we validate the benefits of using antipodally invariant metrics, most of the binary splits use Euclidean distance, which does not handle antipodes optimally. In order to benefit from both the worlds, we propose a simple yet effective antipodally invariant transform that can be easily included in the Euclidean distance calculation. We modify the original spherical hashing algorithm with this metric in our antipodally invariant spherical hashing scheme, obtaining the same performance as a pure antipodally invariant metric. We round up our contributions with a novel feature transform that obtains a better coarse approximation of the input image thanks to iterative backprojection. The performance of our method, which we named antipodally invariant SR, improves quality (Peak Signal to Noise Ratio) and it is faster than any other state-of-the-art method. [ABSTRACT FROM AUTHOR]

Vehicle lane-level localization is a fundamental technology in autonomous driving. To achieve accurate and consistent performance, a common approach is to use the LIDAR technology. However, it is expensive and computational demanding, and thus not a practical solution in many situations. This paper proposes a stereovision system, which is of low cost, yet also able to achieve high accuracy and consistency. It integrates a new lane line detection algorithm with other lane marking detectors to effectively identify the correct lane line markings. It also fits multiple road models to improve accuracy. An effective stereo 3D reconstruction method is proposed to estimate vehicle localization. The estimation consistency is further guaranteed by a new particle filter framework, which takes vehicle dynamics into account. Experiment results based on image sequences taken under different visual conditions showed that the proposed system can identify the lane line markings with 98.6% accuracy. The maximum estimation error of the vehicle distance to lane lines is 16 cm in daytime and 26 cm at night, and the maximum estimation error of its moving direction with respect to the road tangent is 0.06 rad in daytime and 0.12 rad at night. Due to its high accuracy and consistency, the proposed system can be implemented in autonomous driving vehicles as a practical solution to vehicle lane-level localization. [ABSTRACT FROM AUTHOR]

Recently, sparse signal representation of image patches has been explored to solve the pansharpening problem. Although these proposed sparse-reconstruction-based methods lead to promising results, three issues remained unsolved: 1) high computational cost; 2) no consideration given to the possibility of mutually correlated information in different multispectral channels; and 3) requirement that the spectral responses of the panchromatic (Pan) image and the multispectral image cover the same wavelength range, which is not necessarily valid for most sensors. In this paper, we propose a sophisticated sparse image fusion algorithm, which is named “jointly sparse fusion of images” (J-SparseFI). It is based on the earlier proposed sparse fusion of images (SparseFI) algorithm and overcomes the aforementioned three drawbacks of the existing sparse image fusion algorithms. The computational problem is handled by reducing the problem size and by proposing a fully parallelizable scheme. Moreover, J-SparseFI exploits the possible signal structure correlations between multispectral channels by introducing the joint sparsity model (JSM) and sharpening the highly correlated adjacent multispectral channels together. This is done by exploiting the distributed compressive sensing theory that restricts the solution of an underdetermined system by considering an ensemble of signals being jointly sparse. J-SparseFI also offers a practical solution to overcome spectral range mismatch between the Pan and multispectral images. By means of sensor spectral response and channel mutual correlation analysis, the multispectral channels are assigned to primary groups of joint channels, secondary groups of joint channels, and individual channels. Primary groups of joint channels, individual channels, and secondary groups of joint channels are then reconstructed sequentially, by the JSM or by modified SparseFI, using a dictionary trained from the Pan image or previously reconstructed high-resolution multispectral channels. A recipe of how to choose appropriate algorithm parameters, including the most crucial regularization parameter, is provided. The algorithm is evaluated and validated using WorldView-2-like images that are simulated using very high resolution airborne HySpex hyperspectral imagery and further practically demonstrated using real WorldView-2 images. The algorithm's performance is compared with other state-of-the-art methods. Visual and quantitative analyses demonstrate the high quality of the proposed method. In particular, the analysis of the difference images suggests that J-SparseFI is superior in image resolution recovery. [ABSTRACT FROM AUTHOR]

This paper presents a novel single image super-resolution (SR) reconstruction method using shifted kernel regression. Assuming that a low-resolution (LR) image is made by the shifted regression-based image degradation model, the proposed SR process shifts pixels in a regularly sampled LR image with a subpixel precision according to local gradient. The optimum displacement of each pixel is estimated using the Gaussian filtered second derivatives. The shifted low-resolution image is finally up-scaled by estimating the regression coefficients of the shifted kernels in the spatially adaptive manner. Experimental results show that the proposed method overcomes the limitation of existing intensity-based SR algorithms. The proposed SR algorithm can successfully restore sharp, clear edges without undesired artifacts such as ringing, inverted gradient, halo effects, etc. Without using an iterative process, the proposed single image SR algorithm can easily be implemented in the form of either pre- or post-processing filters for further enhancing the SR result of existing methods. [ABSTRACT FROM AUTHOR]

Phase-diversity (PD) is the least square adaptive-filter of the imaging system based on wave optics theory. It can use unknown extended object as the observation object to collect two or more images whose wave-front diversities are known and fixed. According to the images, the wave-front of the optical system can be calculated by PD, and simultaneously the estimation of ideal image for the observation object can be obtained. Phase-diverse speckle (PDS) technique extends PD by using a series of short-expose frames as the input. In this paper, we designed PDS experiment on a 1.23 m telescope and successfully got clear restored images of space objects. Under the observation condition that the atmospheric coherent length was not more than 8 cm at 500 nm wavelength in Changchun city, we replaced the deformable mirror with a plane mirror in adaptive optical system and separately used the moon and Polaris as the observation objects. For Polaris, the FWHW reduced from 20.6 to 5.3 (in pixel), which decreased about 74%. The experimental results demonstrate that PDS algorithm can be used on one meter-scale telescope in practical observation. [ABSTRACT FROM AUTHOR]