Search

Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing and communications applications, including denoising, spectrum sensing, and compression. Notice that estimating the covariance matrix from compressive samples leads to ill-posed minimizations with severe performance loss at high compression rates. In this regard, a regularization term is typically aggregated to the cost function to consider prior information about a particular property of the covariance matrix. Hence, this paper proposes an algorithm based on the projected gradient method to recover low-rank or Toeplitz approximations of the covariance matrix from compressive measurements. The proposed algorithm divides the compressive measurements into data subsets projected onto different subspaces and accurately estimates the covariance matrix by solving a single optimization problem assuming that each data subset contains an approximation of the signal statistics. Furthermore, gradient filtering is included at every iteration of the proposed algorithm to minimize the estimation error. The error induced by the proposed splitting approach is analytically derived along with the convergence guarantees of the proposed method. The proposed algorithm estimates the covariance matrix of hyperspectral images from synthetic and real compressive samples. Extensive simulations show that the proposed algorithm can effectively recover the covariance matrix of hyperspectral images from compressive measurements with high compression ratios ($8-15\%$ approx) in noisy scenarios. Moreover, simulations and theoretical results show that the filtering step reduces the recovery error up to twice the number of eigenvectors. Finally, an optical implementation is proposed, and real measurements are used to validate the theoretical findings. [ABSTRACT FROM AUTHOR]

Numerous single image super-resolution (SISR) algorithms have been proposed during the past years to reconstruct a high-resolution (HR) image from its low-resolution (LR) observation. However, how to fairly compare the performance of different SISR algorithms/results remains a challenging problem. So far, the lack of comprehensive human subjective study on large-scale real-world SISR datasets and accurate objective SISR quality assessment metrics makes it unreliable to truly understand the performance of different SISR algorithms. We in this paper make efforts to tackle these two issues. Firstly, we construct a real-world SISR quality dataset (i.e., RealSRQ) and conduct human subjective studies to compare the performance of the representative SISR algorithms. Secondly, we propose a new objective metric, i.e., KLTSRQA, based on the Karhunen-Loéve Transform (KLT) to evaluate the quality of SISR images in a no-reference (NR) manner. Experiments on our constructed RealSRQ and the latest synthetic SISR quality dataset (i.e., QADS) have demonstrated the superiority of our proposed KLTSRQA metric, achieving higher consistency with human subjective scores than relevant existing NR image quality assessment (NR-IQA) metrics. The dataset and the code will be made available at https://github.com/Zhentao-Liu/RealSRQ-KLTSRQA. [ABSTRACT FROM AUTHOR]

Weighted multi-view clustering (MVC) aims to combine the complementary information of multi-view data (such as image data with different types of features) in a weighted manner to obtain a consistent clustering result. However, when the cluster-wise weights across views are vastly different, most existing weighted MVC methods may fail to fully utilize the complementary information, because they are based on view-wise weight learning and can not learn the fine-grained cluster-wise weights. Additionally, extra parameters are needed for most of them to control the weight distribution sparsity or smoothness, which are hard to tune without prior knowledge. To address these issues, in this paper we propose a novel and effective Cluster-weighted mUlti-view infoRmation bottlEneck (CURE) clustering algorithm, which can automatically learn the cluster-wise weights to discover the discriminative clusters across multiple views and thus can enhance the clustering performance by properly exploiting the cluster-level complementary information. To learn the cluster-wise weights, we design a new weight learning scheme by exploring the relation between the mutual information of the joint distribution of a specific cluster (containing a group of data samples) and the weight of this cluster. Finally, a novel draw-and-merge method is presented to solve the optimization problem. Experimental results on various multi-view datasets show the superiority and effectiveness of our cluster-wise weighted CURE over several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

An improved and extended version of a quaternion-based lossless encryption technique for digital image and communication on medicine (DICOM) images is proposed. We highlight and address several security flaws present in the previous version of the algorithm originally proposed by Dzwonkowski et al. (2015). The newly proposed secure quaternion Feistel cipher (S-QFC) algorithm retains the concept of a modified Feistel network with modular arithmetic and the use of special properties of quaternions to perform rotations of data sequences in 3D space for each of the cipher rounds. A new and more secure key generation scheme based on quaternion Julia sets is utilized. We also introduce both-sided modular matrix multiplications for the encryption and decryption processes. The proposed S-QFC algorithm eliminates the major security flaws of its predecessor while maintaining high computation speed in comparison to other algorithms originally embedded in DICOM (i.e., advanced encryption standard and triple data encryption standard). A computer-based analysis has been carried out. Simulation results and cryptanalysis are shown at the end of this paper. [ABSTRACT FROM AUTHOR]

When imaging through a semi-reflective medium such as glass, the reflection of another scene can often be found in the captured images. It degrades the quality of the images and affects their subsequent analyses. In this paper, a novel deep neural network approach for solving the reflection problem in imaging is presented. Traditional reflection removal methods not only require long computation time for solving different optimization functions, their performance is also not guaranteed. As array cameras are readily available in nowadays imaging devices, we first suggest in this paper a multiple-image based depth estimation method using a convolutional neural network (CNN). The proposed network avoids the depth ambiguity problem due to the reflection in the image, and directly estimates the depths along the image edges. They are then used to classify the edges as belonging to the background or reflection. Since edges having similar depth values are error prone in the classification, they are removed from the reflection removal process. We suggest a generative adversarial network (GAN) to regenerate the removed background edges. Finally, the estimated background edge map is fed to another auto-encoder network to assist the extraction of the background from the original image. Experimental results show that the proposed reflection removal algorithm achieves superior performance both quantitatively and qualitatively as compared to the state-of-the-art methods. The proposed algorithm also shows much faster speed compared to the existing approaches using the traditional optimization methods. [ABSTRACT FROM AUTHOR]

Video-based human action recognition is currently one of the most active research areas in computer vision. Various research studies indicate that the performance of action recognition is highly dependent on the type of features being extracted and how the actions are represented. Since the release of the Kinect camera, a large number of Kinect-based human action recognition techniques have been proposed in the literature. However, there still does not exist a thorough comparison of these Kinect-based techniques under the grouping of feature types, such as handcrafted versus deep learning features and depth-based versus skeleton-based features. In this paper, we analyze and compare 10 recent Kinect-based algorithms for both cross-subject action recognition and cross-view action recognition using six benchmark datasets. In addition, we have implemented and improved some of these techniques and included their variants in the comparison. Our experiments show that the majority of methods perform better on cross-subject action recognition than cross-view action recognition, that the skeleton-based features are more robust for cross-view recognition than the depth-based features, and that the deep learning features are suitable for large datasets. [ABSTRACT FROM AUTHOR]

Face Super-Resolution (FSR) aims to infer High-Resolution (HR) face images from the captured Low-Resolution (LR) face image with the assistance of external information. Existing FSR methods are less effective for the LR face images captured with serious low-quality since the huge imaging/degradation gap caused by the different imaging scenarios (i.e., the complex practical imaging scenario that generates test LR images, the simple manual imaging degradation that generates the training LR images) is not considered in these algorithms. In this paper, we propose an image homogenization strategy via re-expression to solve this problem. In contrast to existing methods, we propose a homogenization projection in LR space and HR space as compensation for the classical LR/HR projection to formulate the FSR in a multi-stage framework. We then develop a re-expression process to bridge the gap between the complex degradation and the simple degradation, which can remove the heterogeneous factors such as serious noise and blur. To further improve the accuracy of the homogenization, we extract the image patch set that is invariant to degradation changes as Robust Neighbor Resources (RNR), with which these two homogenization projections re-express the input LR images and the initial inferred HR images successively. Both quantitative and qualitative results on the public datasets demonstrate the effectiveness of the proposed algorithm against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Defocus blur detection (DBD), which has been widely applied to various fields, aims to detect the out-of-focus or in-focus pixels from a single image. Despite the fact that the deep learning based methods applied to DBD have outperformed the hand-crafted feature based methods, the performance cannot still meet our requirement. In this paper, a novel network is established for DBD. Unlike existing methods which only learn the projection from the in-focus part to the ground-truth, both in-focus and out-of-focus pixels, which are completely and symmetrically complementary, are taken into account. Specifically, two symmetric branches are designed to jointly estimate the probability of focus and defocus pixels, respectively. Due to their complementary constraint, each layer in a branch is affected by an attention obtained from another branch, effectively learning the detailed information which may be ignored in one branch. The feature maps from these two branches are then passed through a unique fusion block to simultaneously get the two-channel output measured by a complementary loss. Additionally, instead of estimating only one binary map from a specific layer, each layer is encouraged to estimate the ground truth to guide the binary map estimation in its linked shallower layer followed by a top-to-bottom combination strategy, gradually exploiting the global and local information. Experimental results on released datasets demonstrate that our proposed method remarkably outperforms state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Hyperspectral imagery (HSI) has shown promising results in real-world applications. However, the technological evolution of optical sensors poses two main challenges in HSI classification: 1) the spectral band is usually redundant and noisy and 2) HSI with millions of pixels has become increasingly common in real-world applications. Motivated by the recent success of hybrid huberized support vector machines (HHSVMs), which inherit the benefits of both lasso and ridge regression, this paper first investigates the advantages of HHSVM for HSI applications. Unfortunately, the existing HHSVM solvers suffer from prohibitive computational costs on large-scale data sets. To solve this problem, this paper proposes simple and effective stochastic HHSVM algorithms for HSI classification. In the stochastic settings, we show that with a probability of at least $1-\varrho $ , our algorithms find an $\epsilon $ -accurate solution using $\tilde {O}({1}/{\lambda _{2}\epsilon })$ iterations. Since the convergence rate of our algorithms does not depend on the size of the training set, our algorithms are suitable for handling large-scale problems. We demonstrate the superiority of our algorithms by conducting experiments on large-scale binary and multiclass classification problems, comparing to the state-of-the-art HHSVM solvers. Finally, we apply our algorithms to real HSI classification and achieve promising results. [ABSTRACT FROM AUTHOR]

This paper revisits the problem of rate distortion optimization (RDO) with focus on inter-picture dependence. A joint RDO framework which incorporates the Lagrange multiplier as one of parameters to be optimized is proposed. Simplification strategies are demonstrated for practical applications. To make the problem tractable, we consider an approach where prediction residuals of pictures in a video sequence are assumed to be emitted from a finite set of sources. Consequently the RDO problem is formulated as finding optimal coding parameters for a finite number of sources, regardless of the length of the video sequence. Specifically, in cases where a hierarchical prediction structure is used, prediction residuals of pictures at the same prediction layer are assumed to be emitted from a common source. Following this approach, we propose an iterative algorithm to alternatively optimize the selections of quantization parameters (QPs) and the corresponding Lagrange multipliers. Based on the results of the iterative algorithm, we further propose two practical algorithms to compute QPs and the Lagrange multipliers for the RA(random access) hierarchical video coding: the first practical algorithm uses a fixed formula to compute QPs and the Lagrange multipliers, and the second practical algorithm adaptively adjusts both QPs and the Lagrange multipliers. Experimental results show that these three algorithms, integrated into the HM 16.20 reference software of HEVC, can achieve considerable RD improvements over the standard HM 16.20 encoder, in the common RA test configuration. [ABSTRACT FROM AUTHOR]

In this paper, we propose a just noticeable distortion (JND)-based perceptual rate control method for high efficiency video coding (HEVC). First, the JND factor of a coding unit has been mathematically shown to be an approximation of the average pixel-level JND weight, which means that it can also be used as a weight for bitrate allocation. Second, rate-distortion (R-D) modelling is conducted based on the JND factor. Finally, the proposed R-D model is integrated into an existing rate control framework to improve the coding efficiency, and the proposed algorithm is implemented in the newest video coding standard. As the experimental results reveal, compared with HEVC reference software, our algorithm achieves significantly improved coding performance, subjective coding quality and bitrate accuracy. [ABSTRACT FROM AUTHOR]

Salient object detection has undergone a very rapid development with the blooming of Deep Neural Network (DNN), which is usually taken as an important preprocessing procedure in various computer vision tasks. However, the down-sampling operations, such as pooling and striding, always make the final predictions blurred at edges, which has seriously degenerated the performance of salient object detection. In this paper, we propose a simple yet effective approach, i.e., Hierarchical and Interactive Refinement Network (HIRN), to preserve the edge structures in detecting salient objects. In particular, a novel multi-stage and dual-path network structure is designed to estimate the salient edges and regions from the low-level and high-level feature maps, respectively. As a result, the predicted regions will become more accurate by enhancing the weak responses at edges, while the predicted edges will become more semantic by suppressing the false positives in background. Once the salient maps of edges and regions are obtained at the output layers, a novel edge-guided inference algorithm is introduced to further filter the resulting regions along the predicted edges. Extensive experiments on several benchmark datasets have been conducted, in which the results show that our method significantly outperforms a variety of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Image acquisition in many biomedical imaging modalities is corrupted by Poisson noise followed by additive Gaussian noise. While total variation and related regularization methods for solving biomedical inverse problems are known to yield high quality reconstructions in most situations, such methods mostly use log-likelihood of either Gaussian or Poisson noise models, and rarely use mixed Poisson-Gaussian (PG) noise model. There is a recent work which deals with exact PG likelihood and total variation regularization. This method adapts the primal-dual approach involving gradients steps on the PG log-likelihood, with step size limited by the inverse of its Lipschitz constant. This leads to limitations in the convergence speed. Although the alternating direction method of multipliers (ADMM) algorithm does not have such step size restrictions, ADMM has never been applied for this problem, for the possible reason that PG log-likelihood is quite complex. In this paper, we develop an ADMM based optimization for roughness minimizing image restoration under PG log-likelihood. We achieve this by first developing a novel iterative method for computing the proximal solution of PG log-likelihood, deriving the termination conditions for this iterative method, and then integrating into a provably convergent ADMM scheme. We experimentally demonstrate that the proposed method outperform primal-dual method in most of the cases. [ABSTRACT FROM AUTHOR]

Connected component labeling (CCL) is a fundamental image processing problem that has been studied in many platforms, including GPUs. A common approach to CCL performance analysis is studying the total processing time as a function of abstract image features, like the number of connected components or the fraction of foreground pixels, and input data usually includes synthetic images and segmented video datasets. In this paper, we develop on these ideas and propose an evaluation methodology for GPU CCL algorithms based on synthetic image patterns, addressing the nonexistence of a standard and reliable benchmark in the literature. Our methodology, applied on two important algorithms from existing literature, uncovers their data dependency with great detail, and allows us to model their processing time in three real-world video data sets as functions of abstract, high-level image concepts. We also apply our methodology for studying the memory and performance requirements of two strategies for computing connected component properties: an existing memory-hungry approach, and a new memory-preserving strategy. [ABSTRACT FROM AUTHOR]

Milano Retinex is a family of spatial color algorithms inspired by Retinex and mainly devoted to the image enhancement. In the so-called point-based sampling Milano Retinex algorithms, this task is accomplished by processing the color of each image pixel based on a set of colors sampled in its surround. This paper presents STAR, a segmentation based approximation of the point-based sampling Milano Retinex approaches: it replaces the pixel-wise image sampling by a novel, computationally efficient procedure that detects once for all the color and spatial information relevant to image enhancement from clusters of pixels output by a segmentation. The experiments reported here show that STAR performs similarly to previous point-based sampling Milano Retinex approaches and that STAR enhancement improves the accuracy of the well-known algorithm scale-invariant feature transform on the description and matching of photographs captured under difficult light conditions. [ABSTRACT FROM AUTHOR]

This paper presents a fast and effective polarization image demosaicking algorithm, which explores inter-channel dependency of Stokes parameters for the minimization of residual aliasing artifacts after cubic spline interpolation. A guided filtering approach is used for denoising. An optimization based on the confidence level of the aforementioned guided filtering, the correlations between the demosaicked image and input, as well as the total intensity, angle and degree of linear polarization, is constructed and solved with Newton’s method. Experimental results demonstrate that the proposed algorithm can surpass the existing methods in terms of both objective root mean squared error and structural similarity index by at least 36.0% and 3.4%, respectively, and by close visual inspection of the clarity of objects in the angle and degree of linear polarization images. The proposed algorithm consists of only convolutions and element-wise operations, making it fast and parallelizable for efficient GPU acceleration. An image of size $512\times 612\times 4$ can be processed within 10 s on i7-6700k CPU, and gains further 5 times speedup with M4000M GPU. [ABSTRACT FROM AUTHOR]

Introducing spatial prior information in hyperspectral imaging (HSI) analysis has led to an overall improvement of the performance of many HSI methods applied for denoising, classification, and unmixing. Extending such methodologies to nonlinear settings is not always straightforward, specially for unmixing problems where the consideration of spatial relationships between neighboring pixels might comprise intricate interactions between their fractional abundances and nonlinear contributions. In this paper, we consider a multiscale regularization strategy for nonlinear spectral unmixing with kernels. The proposed methodology splits the unmixing problem into two sub-problems at two different spatial scales: a coarse scale containing low-dimensional structures, and the original fine scale. The coarse spatial domain is defined using superpixels that result from a multiscale transformation. Spectral unmixing is then formulated as the solution of quadratically constrained optimization problems, which are solved efficiently by exploring their strong duality and a reformulation of their dual cost functions in the form of root-finding problems. Furthermore, we employ a theory-based statistical framework to devise a consistent strategy to estimate all required parameters, including both the regularization parameters of the algorithm and the number of superpixels of the transformation, resulting in a truly blind (from the parameters setting perspective) unmixing method. Experimental results attest the superior performance of the proposed method when comparing with other, state-of-the-art, related strategies. [ABSTRACT FROM AUTHOR]

The traditional salient object detection models can be divided into several classes based on the low-level features of images and contrast between the pixels. This paper proposes an adversarial learning model (ALM) that includes the generative model and discriminative model. The ALM uses the original image as an input of the generative model to extract the high-level features and forms an initial salient map. Then, the discriminative model is utilized to compare differences in the features between the initial salient map and the ground truth, and the obtained differences are sent to the convolutional layers of the generative model to adjust the parameters for the generative model updating. Due to the serial-iterative adjustment, the salient map of the generative model becomes more similar to the ground truth. Lastly, the ALM forms the salient map fused with the super-pixels by enhancing the color and texture features, so the final salient map is obtained. The ALM is not limited to the color and texture features; on the contrary, it fuses multiple features and achieves good results in the salient target extraction. The experimental results show that ALM performs better than the other ten state-of-the-art models on three different datasets. Thus, the proposed ALM is widely applicable to the salient target extraction. [ABSTRACT FROM AUTHOR]

Image feature correspondence selection is pivotal to many computer vision tasks from object recognition to 3D reconstruction. Although many correspondence selection algorithms have been developed in the past decade, there still lacks an in-depth evaluation and comparison in the open literature, which makes it difficult to choose the appropriate algorithm for a specific application. This paper attempts to fill this gap by evaluating eight competing correspondence selection algorithms including both classical methods and current state-of-the-art ones. In addition to preselected correspondences, we have compared different combinations of detector and descriptor on four standard datasets. The diversity of those datasets cover a wide range of uncertainty factors including zoom, rotation, blur, viewpoint change, JPEG compression, light change, different rendering styles and multiple structures. We have measured the quality of competing correspondence selection algorithms in terms of four performance metrics - i.e., precision, recall, F-measure and efficiency. Moreover, we propose to combine the strengths of eight competing methods by combining their correspondence selection results. Extensive experimental results are reported to demonstrate the superiority of several fusion strategies to individual methods, which suggests the possibility of adaptively combining those methods for even better performance. [ABSTRACT FROM AUTHOR]

The recent boost in undersea operations has led to the development of high-resolution sonar systems mounted on autonomous vehicles. These vehicles are used to scan the seafloor in search of different objects such as sunken ships, archaeological sites, and submerged mines. An important part of the detection operation is the segmentation of sonar images, where the object’s highlight and shadow are distinguished from the seabed background. In this paper, we focus on the automatic segmentation of sonar images. We present our enhanced fuzzy-based with Kernel metric (EnFK) algorithm for the segmentation of sonar images which, in an attempt to improve segmentation accuracy, introduces two new fuzzy terms of local spatial and statistical information. Our algorithm includes a preliminary de-noising algorithm which, together with the original image, feeds into the segmentation procedure to avoid trapping to local minima and to improve convergence. The result is a segmentation procedure that specifically suits the intensity inhomogeneity and the complex seabed texture of sonar images. We tested our approach using simulated images, real sonar images, and sonar images that were created in two different sea experiments, using multibeam sonar and synthetic aperture sonar. The results show accurate segmentation performance that is far beyond the state-of-the-art results. [ABSTRACT FROM AUTHOR]

Compressive spectral video sensing (CSVS) systems obtain spatial, spectral, and temporal information of a dynamic scene through the encoding of the incoming light rays by using a temporal-static coded aperture (CA). CSVS systems use CAs with binary entries spatially distributed at random. The random spatial encoding of the binary CAs entails a poor quality in the reconstructed images even though the CSVS sensing matrix is incoherent with the sparse representation basis. In addition, since some pixels are totally blocked, information such as object motion is missed over time. This paper substitutes the temporal-static binary coded apertures by a richer spatio-spectro-temporal encoding based on selectable color filters, named temporal colored coded apertures (T-CCA). The spatial, spectral, and time distributions of the T-CCAs are optimized by better satisfying the restricted isometry property (RIP) of the CSVS system. The RIP-optimized T-CCAs lead to spatio-spectral-time structures that tend to sense more uniformly the spatial, spectral, and temporal dimensions. An algorithm for optimally designing the T-CCAs is developed. In addition, a regularization term based on the scene motion is included in the inverse problem leading to a better quality of the reconstructed images. Computational experiments using four different spectral videos show an improvement of up to 6 dB in terms of peak signal-to-noise ratio of the reconstructed images by using the proposed inverse problem and the T-CCA patterns compared with the binary CAs and random and image-optimized CCA patterns. [ABSTRACT FROM AUTHOR]

The tensor completion issues have obtained a great deal of attention in the past few years. However, the data fidelity part minimizes a squared loss function, which may be inappropriate for the case of noisy one-bit observations. In this paper, we alleviate the mentioned difficulty by drawing on the experience of matrix scenarios. Based on the convex relation to $\ell _{1}$ norm of the tensor multi-rank, we propose a novel optimization model trying to recover the underlying tensor in case of one-bit observations. The feasibility of this model is proved by theoretical derivations. Furthermore, an alternating direction method of multipliers based algorithm is designed to find the solution. The numerical experiments demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Mismatch removal is a key step in many computer vision problems that involve point matching. The existing methods for checking geometric consistency mainly focus on similarity or affine transformations. In this paper, we propose a novel mismatch removal method that can cope with the projective transformation between two corresponding point sets. Our approach is based on the augmented homogeneous coordinates matrix constructed from the coordinates of anchor matches, whose degeneracy can indicate the correctness of anchor matches. The set of anchor matches is initially all the matches and is iteratively updated by calculating the difference between the estimated matched points, which can be easily computed in a closed form, and the actually matched points and removing those with large differences. Experimental results on synthetic 2D point matching data sets and real image matching data sets verify that our method achieves the highest $F$ -score among all the methods under similarity, affine, and projective transformations with noises and outliers. Our method can also achieve faster speed than all other iterative methods. Those non-iterative methods with slight advantage in speed are not competitive in accuracy when compared with ours. We also show that the set of anchor matches is stable through the iteration and the computation time grows very slowly with respect to the number of matched points. When applied to mismatch removal in partial-duplicate image search, our method achieves the best retrieval precision, and its computing time is also highly competitive. [ABSTRACT FROM AUTHOR]

Recently, an important set of high dimensional signals (HDS) applications has successfully implemented compressive sensing (CS) sensors in which their efficiency depends on physical elements that perform a binary codification over the HDS. The structure of the binary codification is crucial as it determines the HDS sensing matrices. For a correct reconstruction, this class of matrices drastically differs from the dense or i.i.d. assumptions usually made in CS. Therefore, current CS matrix design algorithms are impractical. This paper proposes a novel strategy to design structured, sparse, and binary HDS measurement matrices based on promoting linear independence between rows by minimizing the number of its zero singular values. The design constraints lead to keep uniform both, the number of non-zero elements per row and also the number of non-zero elements per column. An algorithm based on an optimal selection of non-zero entries positions is developed to implement this strategy. Simulations show that the proposed optimization improves the quality of the reconstructed HDS in up to 8 dB of PSNR compared with non-optimized matrices. [ABSTRACT FROM AUTHOR]

Blind source separation (BSS) aims to discover the underlying source signals from a set of linear mixture signals without any prior information of the mixing system, which is a fundamental problem in signal and image processing field. Most of the state-of-the-art algorithms have independently handled the decompositions of mixture signals. In this paper, we propose a new algorithm named multi-task sparse model to solve the BSS problem. Source signals are characterized via sparse techniques. Meanwhile, we regard the decomposition of each mixture signal as a task and employ the idea of multi-task learning to discover connections between tasks for the accuracy improvement of the source signal separation. Theoretical analyses on the optimization convergence and sample complexity of the proposed algorithm are provided. Experimental results based on extensive synthetic and real-world data demonstrate the necessity of exploiting connections between mixture signals and the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper considers online robust principal component analysis (RPCA) in time-varying decomposition problems such as video foreground-background separation. We propose a compressive online RPCA algorithm that decomposes recursively a sequence of data vectors (e.g., frames) into sparse and low-rank components. Different from conventional batch RPCA, which processes all the data directly, our approach considers a small set of measurements taken per data vector (frame). Moreover, our algorithm can incorporate multiple prior information from previous decomposed vectors via proposing an $n$ - $\ell _{1}$ minimization method. At each time instance, the algorithm recovers the sparse vector by solving the $n$ - $\ell _{1}$ minimization problem—which promotes not only the sparsity of the vector but also its correlation with multiple previously recovered sparse vectors—and, subsequently, updates the low-rank component using incremental singular value decomposition. We also establish theoretical bounds on the number of measurements required to guarantee successful compressive separation under the assumptions of static or slowly changing low-rank components. We evaluate the proposed algorithm using numerical experiments and online video foreground-background separation experiments. The experimental results show that the proposed method outperforms the existing methods. [ABSTRACT FROM AUTHOR]

Many patch-based image denoising algorithms can be formulated as applying a smoothing filter to the noisy image. Expressed as matrices, the smoothing filters must be row normalized, so that each row sums to unity. Surprisingly, if we apply a column normalization before the row normalization, the performance of the smoothing filter can often be significantly improved. Prior works showed that such performance gain is related to the Sinkhorn–Knopp balancing algorithm, an iterative procedure that symmetrizes a row-stochastic matrix to a doubly stochastic matrix. However, a complete understanding of the performance gain phenomenon is still lacking. In this paper, we study the performance gain phenomenon from a statistical learning perspective. We show that Sinkhorn–Knopp is equivalent to an expectation-maximization (EM) algorithm of learning a Gaussian mixture model of the image patches. By establishing the correspondence between the steps of Sinkhorn–Knopp and the EM algorithm, we provide a geometrical interpretation of the symmetrization process. This observation allows us to develop a new denoising algorithm called Gaussian mixture model symmetric smoothing filter (GSF). GSF is an extension of the Sinkhorn–Knopp and is a generalization of the original smoothing filters. Despite its simple formulation, GSF outperforms many existing smoothing filters and has a similar performance compared with several state-of-the-art denoising algorithms. [ABSTRACT FROM PUBLISHER]

Minimum-cost flow algorithms have recently achieved state-of-the-art results in multi-object tracking. However, they rely on the whole image sequence as input. When deployed in real-time applications or in distributed settings, these algorithms first operate on short batches of frames and then stitch the results into full trajectories. This decoupled strategy is prone to errors because the batch-based tracking errors may propagate to the final trajectories and cannot be corrected by other batches. In this paper, we propose a greedy batch-based minimum-cost flow approach for tracking multiple objects. Unlike existing approaches that conduct batch-based tracking and stitching sequentially, we optimize consecutive batches jointly so that the tracking results on one batch may benefit the results on the other. Specifically, we apply a generalized minimum-cost flows (MCF) algorithm on each batch and generate a set of conflicting trajectories. These trajectories comprise the ones with high probabilities, but also those with low probabilities potentially missed by detectors and trackers. We then apply the generalized MCF again to obtain the optimal matching between trajectories from consecutive batches. Our proposed approach is simple, effective, and does not require training. We demonstrate the power of our approach on data sets of different scenarios. [ABSTRACT FROM PUBLISHER]

Visual attention is an important mechanism in the human visual system (HVS) and there have been numerous saliency detection algorithms designed for 2D images/video recently. However, the research for fixation detection of stereoscopic video is still limited and challenging due to the complicated depth and motion information. In this paper, we design a novel multi-module fully convolutional network (MM-FCN) for fixation detection of stereoscopic video. Specifically, we design a fully convolutional network for spatial saliency prediction (S-FCN), where the initial spatial saliency map of stereoscopic video is learned by image database of object detection. Furthermore, the fully convolutional network for temporal saliency prediction (T-FCN) is constructed by combining saliency results from S-FCN and motion information from video frames. Finally, the fully convolutional network for depth fixation prediction (D-FCN) is designed to compute the final fixation map of stereoscopic video by learning depth features with spatiotemporal features from T-FCN. The experimental results show that the proposed MM-FCN can predict fixation results for stereoscopic video more effectively and efficiently than other related fixation prediction methods. [ABSTRACT FROM AUTHOR]

Image mosaicking applications require both geometrical and photometrical registrations between the images that compose the mosaic. This paper proposes a probabilistic color correction algorithm for correcting the photometrical disparities. First, the image to be color corrected is segmented into several regions using mean shift. Then, connected regions are extracted using a region fusion algorithm. Local joint image histograms of each region are modeled as collections of truncated Gaussians using a maximum likelihood estimation procedure. Then, local color palette mapping functions are computed using these sets of Gaussians. The color correction is performed by applying those functions to all the regions of the image. An extensive comparison with ten other state of the art color correction algorithms is presented, using two different image pair data sets. Results show that the proposed approach obtains the best average scores in both data sets and evaluation metrics and is also the most robust to failures. [ABSTRACT FROM AUTHOR]

Attention deficit hyperactivity disorder (ADHD) is one of the most common childhood mental disorders. Hyperactivity is a typical symptom of ADHD in children. Clinicians diagnose this symptom by evaluating the children’s activities based on subjective rating scales and clinical experience. In this work, an objective system is proposed to quantify the movements of children with ADHD automatically. This system presents a new movement detection and quantification method based on depth images. A novel salient object extraction method is proposed to segment body regions. In movement detection, we explore a new local search algorithm to detect any potential motions of children based on three newly designed evaluation metrics. In the movement quantification, two parameters are investigated to quantify the participation degree and the displacements of each body part in the movements. This system is tested by a depth dataset of children with ADHD. The movement detection results of this dataset mainly range from 91.0% to 95.0%. The movement quantification results of children are consistent with the clinical observations. The public MSR Action 3D dataset is tested to validate the performance of this system. [ABSTRACT FROM AUTHOR]

Graph cuts are widely used in computer vision. To speed up the optimization process and improve the scalability for large graphs, Strandmark and Kahl introduced a splitting method to split a graph into multiple subgraphs for parallel computation in both shared and distributed memory models. However, this parallel algorithm (the parallel BK-algorithm) does not have a polynomial bound on the number of iterations and is found to be non-convergent in some cases due to the possible multiple optimal solutions of its sub-problems. To remedy this non-convergence problem, in this paper, we first introduce a merging method capable of merging any number of those adjacent sub-graphs that can hardly reach agreement on their overlapping regions in the parallel BK-algorithm. Based on the pseudo-boolean representations of graph cuts, our merging method is shown to be effectively reused all the computed flows in these sub-graphs. Through both splitting and merging, we further propose a dynamic parallel and distributed graph cuts algorithm with guaranteed convergence to the globally optimal solutions within a predefined number of iterations. In essence, this paper provides a general framework to allow more sophisticated splitting and merging strategies to be employed to further boost performance. Our dynamic parallel algorithm is validated with extensive experimental results. [ABSTRACT FROM PUBLISHER]

Printing with a large number of inks, also called $N$ -ink printing, is a challenging task. The challenges comprise spectral modeling of the printer, color separation, halftoning, and limitations of the amount of inks. Juxtaposed halftoning, a perfectly dot-off-dot halftoning method, has proved to be useful to address some of these challenges. However, for juxtaposed halftones, prediction of colors as a function of ink area coverages has not yet been fully investigated. The goal of this paper is to introduce a spectral prediction model for $N$ -ink juxtaposed-halftone prints. As the area-coverage domain of juxtaposed inks forms a simplex, we propose a cellular subdivision of the area-coverage domain using the barycentric subdivision of simplexes. The barycentric subdivision provides algorithmically straightforward means to design and implement an $N$ -ink color prediction model. Within the subdomain cells, the Yule–Nielsen spectral Neugebauer model is used for the spectral prediction. Our proposed model is highly accurate for prints with a large number of inks while requiring a relatively low number of calibration samples. [ABSTRACT FROM PUBLISHER]

The bilateral filter is a non-linear filter that uses a range filter along with a spatial filter to perform edge-preserving smoothing of images. A direct computation of the bilateral filter requires $O(S)$ operations per pixel, where $S$ is the size of the support of the spatial filter. In this paper, we present a fast and provably accurate algorithm for approximating the bilateral filter when the range kernel is Gaussian. In particular, for box and Gaussian spatial filters, the proposed algorithm can cut down the complexity to $O(1)$ per pixel for any arbitrary $S$ . The algorithm has a simple implementation involving $N+1$ spatial filterings, where $N$ is the approximation order. We give a detailed analysis of the filtering accuracy that can be achieved by the proposed approximation in relation to the target bilateral filter. This allows us to estimate the order $N$ required to obtain a given accuracy. We also present comprehensive numerical results to demonstrate that the proposed algorithm is competitive with the state-of-the-art methods in terms of speed and accuracy. [ABSTRACT FROM AUTHOR]

Video contents are inherently heterogeneous. To exploit different feature modalities in a diverse video collection for video summarization, we propose to formulate the task as a multiview representative selection problem. The goal is to select visual elements that are representative of a video consistently across different views (i.e., feature modalities). We present in this paper the multiview sparse dictionary selection with centroid co-regularization method, which optimizes the representative selection in each view, and enforces that the view-specific selections to be similar by regularizing them towards a consensus selection. We also introduce a diversity regularizer to favor a selection of diverse representatives. The problem can be efficiently solved by an alternating minimizing optimization with the fast iterative shrinkage thresholding algorithm. Experiments on synthetic data and benchmark video datasets validate the effectiveness of the proposed approach for video summarization, in comparison with other video summarization methods and representative selection methods such as K-medoids, sparse dictionary selection, and multiview clustering. [ABSTRACT FROM PUBLISHER]

A nonnegative matrix factorization (NMF) can be computed efficiently under the separability assumption, which asserts that all the columns of the given input data matrix belong to the cone generated by a (small) subset of them. The provably most robust methods to identify these conic basis columns are based on nonnegative sparse regression and self-dictionaries, and require the solution of large-scale convex optimization problems. In this paper, we study a particular nonnegative sparse regression model with self-dictionary. As opposed to previously proposed models, this model yields a smooth optimization problem, where the sparsity is enforced through linear constraints. We show that the Euclidean projection on the polyhedron defined by these constraints can be computed efficiently, and propose a fast gradient method to solve our model. We compare our algorithm with several state-of-the-art methods on synthetic data sets and real-world hyperspectral images. [ABSTRACT FROM PUBLISHER]

Compared with traditional image classification, fine-grained visual categorization is a more challenging task, because it targets to classify objects belonging to the same species, e.g., classify hundreds of birds or cars. In the past several years, researchers have made many achievements on this topic. However, most of them are heavily dependent on the artificial annotations, e.g., bounding boxes, part annotations, and so on. The requirement of artificial annotations largely hinders the scalability and application. Motivated to release such dependence, this paper proposes a robust and discriminative visual description named Automated Bi-level Description (AutoBD). “Bi-level” denotes two complementary part-level and object-level visual descriptions, respectively. AutoBD is “automated,” because it only requires the image-level labels of training images and does not need any annotations for testing images. Compared with the part annotations labeled by the human, the image-level labels can be easily acquired, which thus makes AutoBD suitable for large-scale visual categorization. Specifically, the part-level description is extracted by identifying the local region saliently representing the visual distinctiveness. The object-level description is extracted from object bounding boxes generated with a co-localization algorithm. Although only using the image-level labels, AutoBD outperforms the recent studies on two public benchmark, i.e., classification accuracy achieves 81.6% on CUB-200–2011 and 88.9% on Car-196, respectively. On the large-scale Birdsnap data set, AutoBD achieves the accuracy of 68%, which is currently the best performance to the best of our knowledge. [ABSTRACT FROM PUBLISHER]

A novel primary object discovery (POD) algorithm, which uses reliable object proposals while exploiting the recurrence property of a primary object in a video sequence, is proposed in this paper. First, we generate both color-based and motion-based object proposals in each frame, and extract the feature of each proposal using the random walk with restart simulation. Next, we estimate the foreground confidence for each proposal to remove unreliable proposals. By superposing the features of the remaining reliable proposals, we construct the primary object models. To this end, we develop the evolutionary primary object modeling technique, which exploits the recurrence property of the primary object. Then, using the primary object models, we choose the main proposal in each frame and find the location of the primary object by merging the main proposal with candidate proposals selectively. Finally, we refine the discovered bounding boxes by exploiting temporal correlations of the recurring primary object. Extensive experimental results demonstrate that the proposed POD algorithm significantly outperforms conventional algorithms. [ABSTRACT FROM PUBLISHER]

Hashing has attracted increasing research attention in recent years due to its high efficiency of computation and storage in image retrieval. Recent works have demonstrated the superiority of simultaneous feature representations and hash functions learning with deep neural networks. However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images. The loss of local spatial structure makes the performance bottleneck of hash functions, therefore limiting its application for accurate similarity retrieval. In this paper, we propose a novel deep ordinal hashing (DOH) method, which learns ordinal representations to generate ranking-based hash codes by leveraging the ranking structure of feature space from both local and global views. In particular, to effectively build the ranking structure, we propose to learn the rank correlation space by exploiting the local spatial information from fully convolutional network and the global semantic information from the convolutional neural network simultaneously. More specifically, an effective spatial attention model is designed to capture the local spatial information by selectively learning well-specified locations closely related to target objects. In such hashing framework, the local spatial and global semantic nature of images is captured in an end-to-end ranking-to-hashing manner. Experimental results conducted on three widely used datasets demonstrate that the proposed DOH method significantly outperforms the state-of-the-art hashing methods. [ABSTRACT FROM AUTHOR]

As one of the most widely used clustering techniques, the fuzzy $k$ -means (FKM) assigns every data point to each cluster with a certain degree of membership. However, conventional FKM approach relies on the square data fitting term, which is sensitive to the outliers with ignoring the prior information. In this paper, we develop a novel and robust fuzzy $k$ -means clustering algorithm, namely, joint learning of fuzzy $k$ -means and nonnegative spectral clustering with side information. The proposed method combines fuzzy $k$ -means and nonnegative spectral clustering into a unified model, which can further exploit the prior knowledge of data pairs such that both the quality of affinity graph and the clustering performance can be improved. In addition, for the purpose of enhancing the robustness, the adaptive loss function is adopted in the objective function, since it smoothly interpolates between $\ell _{1}$ -norm and $\ell _{2}$ -norm. Finally, experimental results on benchmark datasets verify the effectiveness and the superiority of our clustering method. [ABSTRACT FROM AUTHOR]

Fractional interpolation is used to provide sub-pixel level references for motion compensation in the interprediction of video coding, which attempts to remove temporal redundancy in video sequences. Traditional handcrafted fractional interpolation filters face the challenge of modeling discontinuous regions in videos, while existing deep learning-based methods are either designed for a single quantization parameter (QP), only generating half-pixel samples, or need to train a model for each sub-pixel position. In this paper, we present a one-for-all fractional interpolation method based on a grouped variation convolutional neural network (GVCNN). Our method can deal with video frames coded using different QPs and is capable of generating all sub-pixel positions at one sub-pixel level. Also, by predicting variations between integer-position pixels and sub-pixels, our network offers more expressive power. Moreover, we perform specific measurements in training data generation to simulate practical situations in video coding, including blurring the down-sampled sub-pixel samples to avoid aliasing effects and coding integer pixels to simulate reconstruction errors. In addition, we analyze the impact of the size of blur kernels theoretically. Experimental results verify the efficiency of GVCNN. Compared with HEVC, our method achieves 2.2% in bit saving on average and up to 5.2% under low-delay P configuration. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have revolutionized the computer vision research and have seen unprecedented adoption for multiple tasks, such as classification, detection, and caption generation. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance. In this paper, we aim at alleviating this opaqueness of CNNs by providing visual explanations for the network’s predictions. Our approach can analyze a variety of CNN-based models trained for computer vision applications, such as object recognition and caption generation. Unlike the existing methods, we achieve this via unraveling the forward pass operation. The proposed method exploits feature dependencies across the layer hierarchy and uncovers the discriminative image locations that guide the network’s predictions. We name these locations CNN fixations, loosely analogous to human eye fixations. Our approach is a generic method that requires no architectural changes, additional training, or gradient computation, and computes the important image locations (CNN fixations). We demonstrate through a variety of applications that our approach is able to localize the discriminative image locations across different network architectures, diverse vision tasks, and data modalities. [ABSTRACT FROM AUTHOR]

To meet the required huge data analysis, organization, and storage demand, the hashing technique has got a lot of attention as it aims to learn an efficient binary representation from the original high-dimensional data. In this paper, we focus on the unsupervised spectral hashing due to its effective manifold embedding. Existing spectral hashing methods mainly suffer from two problems, i.e., the inefficient spectral candidate and intractable binary constraint for spectral analysis. To overcome these two problems, we propose to employ spectral rotation to seek a better spectral solution and adopt the alternating projection algorithm to settle the complex code constraints, which are therefore named as Spectral Hashing with Spectral Rotation and Alternating Discrete Spectral Hashing, respectively. To enjoy the merits of both methods, the spectral rotation technique is finally combined with the original spectral objective, which aims to simultaneously learn better spectral solution and more efficient discrete codes and is called as Discrete Spectral Hashing. Furthermore, the efficient optimization algorithms are also provided, which just take comparable time complexity to existing hashing methods. To evaluate the proposed three methods, extensive comparison experiments and studies are conducted on four large-scale data sets for the image retrieval task, and the noticeable performance beats several state-of-the-art spectral hashing methods on different evaluation metrics. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel depth restoration algorithm from RGB-D data through combining characteristics of local and non-local manifolds, which provide low-dimensional parameterizations of the local and non-local geometry of depth maps. Specifically, on the one hand, a local manifold model is defined to favor local neighboring relationship of pixels in depth, according to which, manifold regularization is introduced to promote smoothing along the manifold structure. On the other hand, the non-local characteristics of the patch-based manifold can be used to build highly data-adaptive orthogonal bases to extract elongated image patterns, accounting for self-similar structures in the manifold. We further define a manifold thresholding operator in 3D adaptive orthogonal spectral bases—eigenvectors of the discrete Laplacian of local and non-local manifolds—to retain only low graph frequencies for depth maps restoration. Finally, we propose a unified alternating direction method of multipliers optimization framework, which elegantly casts the adaptive manifold regularization and thresholding jointly to regularize the inverse problem of depth maps recovery. Experimental results demonstrate that our method achieves superior performance compared with the state-of-the-art works with respect to both objective and subjective quality evaluations. [ABSTRACT FROM AUTHOR]

Depth and surface normal estimation are crucial components in understanding 3D scene geometry from calibrated stereo images. In this paper, we propose visibility and disparity magnitude constraints for slanted patches in the scene. These constraints can be used to associate geometrically feasible planes with each point in the disparity space. The new constraints are validated in the PatchMatch Stereo framework. We use these new constraints not only for initialization, but also in the local plane refinement step of this iterative algorithm. The proposed constraints increase the probability of estimating correct plane parameters, and lead to an improved 3D reconstruction of the scene. Furthermore, the proposed constrained initialization reduces the number of iterations before convergence to the optimal plane parameters. In addition, as most stereo image pairs are not perfectly rectified, we modify the view propagation process by assigning the plane parameters to the neighbors of the candidate pixel. To update the plane parameters in the plane refinement step, we use a gradient free non-linear optimizer. The benefits of the new initialization, propagation, and refinement schemes are demonstrated. [ABSTRACT FROM AUTHOR]

We present a conditional random field approach to tracking-by-detection in which we model pairwise factors linking pairs of detections and their hidden labels, as well as higher order potentials defined in terms of label costs. To the contrary of previous papers, our method considers long-term connectivity between pairs of detections and models similarities as well as dissimilarities between them, based on position, color, and as novelty, visual motion cues. We introduce a set of feature-specific confidence scores, which aim at weighting feature contributions according to their reliability. Pairwise potential parameters are then learned in an unsupervised way from detections or from tracklets. Label costs are defined so as to penalize the complexity of the labeling, based on prior knowledge about the scene like the location of entry/exit zones. Experiments on PETS'09, TUD, CAVIAR, Parking Lot, and Town Center public data sets show the validity of our approach, and similar or better performance than recent state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Blind motion deblurring from a single image is a highly under-constrained problem with many degenerate solutions. A good approximation of the intrinsic image can, therefore, only be obtained with the help of prior information in the form of (often nonconvex) regularization terms for both the intrinsic image and the kernel. While the best choice of image priors is still a topic of ongoing investigation, this research is made more complicated by the fact that historically each new prior requires the development of a custom optimization method. In this paper, we develop a stochastic optimization method for blind deconvolution. Since this stochastic solver does not require the explicit computation of the gradient of the objective function and uses only efficient local evaluation of the objective, new priors can be implemented and tested very quickly. We demonstrate that this framework, in combination with different image priors produces results with Peak Signal-to-Noise Ratio (PSNR) values that match or exceed the results obtained by much more complex state-of-the-art blind motion deblurring algorithms. [ABSTRACT FROM PUBLISHER]

Block-based motion estimation (ME) and motion compensation (MC) techniques are widely used in modern video processing algorithms and compression systems. The great variety of video applications and devices results in diverse compression specifications, such as frame rates and bit rates. In this paper, we study the effect of frame rate and compression bit rate on block-based ME and MC as commonly utilized in inter-frame coding and frame rate up-conversion (FRUC). This joint examination yields a theoretical foundation for comparing MC procedures in coding and FRUC. First, the video signal is locally modeled as a noisy translational motion of an image. Then, we theoretically model the motion-compensated prediction of available and absent frames as in coding and FRUC applications, respectively. The theoretic MC-prediction error is studied further and its autocorrelation function is calculated, yielding useful separable-simplifications for the coding application. We argue that a linear relation exists between the variance of the MC-prediction error and temporal distance. While the relevant distance in MC coding is between the predicted and reference frames, MC-FRUC is affected by the distance between the frames available for interpolation. We compare our estimates with experimental results and show that the theory explains qualitatively the empirical behavior. Then, we use the models proposed to analyze a system for improving of video coding at low bit rates, using a spatio-temporal scaling. Although this concept is practically employed in various forms, so far it lacked a theoretical justification. We here harness the proposed MC models and present a comprehensive analysis of the system, to qualitatively predict the experimental results. [ABSTRACT FROM AUTHOR]

We introduce a novel edge tracing algorithm using Gaussian process regression. Our edge-based segmentation algorithm models an edge of interest using Gaussian process regression and iteratively searches the image for edge pixels in a recursive Bayesian scheme. This procedure combines local edge information from the image gradient and global structural information from posterior curves, sampled from the model’s posterior predictive distribution, to sequentially build and refine an observation set of edge pixels. This accumulation of pixels converges the distribution to the edge of interest. Hyperparameters can be tuned by the user at initialisation and optimised given the refined observation set. This tunable approach does not require any prior training and is not restricted to any particular type of imaging domain. Due to the model’s uncertainty quantification, the algorithm is robust to artefacts and occlusions which degrade the quality and continuity of edges in images. Our approach also has the ability to efficiently trace edges in image sequences by using previous-image edge traces as a priori information for consecutive images. Various applications to medical imaging and satellite imaging are used to validate the technique and comparisons are made with two commonly used edge tracing algorithms. [ABSTRACT FROM AUTHOR]

Style transfer is a process of migrating a style from a given image to the content of another, synthesizing a new image, which is an artistic mixture of the two. Recent work on this problem adopting convolutional neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained. There exists an alternative path toward handling the style transfer task, via the generalization of texture synthesis algorithms. This approach has been proposed over the years, but its results are typically less impressive compared with the CNN ones. In this paper, we propose a novel style transfer algorithm that extends the texture synthesis work of Kwatra et al. (2005), while aiming to get stylized images that are closer in quality to the CNN ones. We modify Kwatra’s algorithm in several key ways in order to achieve the desired transfer, with emphasis on a consistent way for keeping the content intact in selected regions, while producing hallucinated and rich style in others. The results obtained are visually pleasing and diverse, shown to be competitive with the recent CNN style transfer algorithms. The proposed algorithm is fast and flexible, being able to process any pair of content + style images. [ABSTRACT FROM PUBLISHER]