<![CDATA[ IEEE Transactions on Image Processing - Popular ]]>
http://ieeexplore.ieee.org
Popular Articles Alert for this Publication# 83 2017February <![CDATA[A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior]]>2411352235332997<![CDATA[Image quality assessment: from error visibility to structural similarity]]>1346006121726<![CDATA[A Decomposition Framework for Image Denoising Algorithms]]>2513883993720<![CDATA[Shapes From Pixels]]>253119312063037<![CDATA[Perceptual Image Fusion Using Wavelets]]>263107610887225<![CDATA[Image Super-Resolution Via Sparse Representation]]>1911286128731802<![CDATA[Underwater Image Restoration Based on Image Blurriness and Light Absorption]]>264157915945329<![CDATA[Robust Registration of Dynamic Facial Sequences]]>2 norm of the representation as a cue for performing coarse-to-fine registration efficiently. Importantly, the framework can identify registration failures and correct them. Experiments show that the proposed approach achieves significantly higher registration accuracy than the state-of-the-art techniques in challenging sequences.]]>264170817225050<![CDATA[Curvature Filters Efficiently Reduce Certain Variational Energies]]>264178617987552<![CDATA[LIME: Low-Light Image Enhancement via Illumination Map Estimation]]>2629829939437<![CDATA[ViBe: A Universal Background Subtraction Algorithm for Video Sequences]]>206170917242571<![CDATA[Quality Scalability Aware Watermarking for Visual Content]]>25115158517211207<![CDATA[Image Denoising With Edge-Preserving and Segmentation Based on Mask NHA]]>2412602560332989<![CDATA[Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering]]>168208020956170<![CDATA[Appearance-Based Gaze Estimation via Uncalibrated Gaze Pattern Recovery]]>264154315532493<![CDATA[Robust Transfer Metric Learning for Image Classification]]>2626606703165<![CDATA[PCANet: A Simple Deep Learning Baseline for Image Classification?]]>2412501750324347<![CDATA[Active contours without edges]]>102266277508<![CDATA[Salient Object Detection: A Benchmark]]>2412570657228912<![CDATA[Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries]]>1512373637453758<![CDATA[Gamut Extension for Cinema]]>264159516064151<![CDATA[Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions]]>196163516505778<![CDATA[Improved Denoising via Poisson Mixture Modeling of Image Sensor Noise]]>2641565157810435<![CDATA[Haze Removal Using the Difference- Structure-Preservation Prior]]>263106310753627<![CDATA[Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising]]>PP991120210<![CDATA[A Robust and Efficient Approach to License Plate Detection]]>263110211144247<![CDATA[Image information and visual quality]]>1524304446512<![CDATA[$L_{0}$ Gradient Projection]]>0 gradient, the number of the non-zero gradients of an image, together with a quadratic data-fidelity to an input image has been recognized as a powerful edge-preserving filtering method. However, the L_{0} gradient minimization has an inherent difficulty: a user-given parameter controlling the degree of flatness does not have a physical meaning since the parameter just balances the relative importance of the L_{0} gradient term to the quadratic data-fidelity term. As a result, the setting of the parameter is a troublesome work in the L_{0} gradient minimization. To circumvent the difficulty, we propose a new edge-preserving filtering method with a novel use of the L_{0} gradient. Our method is formulated as the minimization of the quadratic data-fidelity subject to the hard constraint that the L_{0} gradient is less than a user-given parameter α. This strategy is much more intuitive than the L_{0} gradient minimization because the parameter α has a clear meaning: the L_{0} gradient value of the output image itself, so that one can directly impose a desired degree of flatness by α. We also provide an efficient algorithm based on the so-called alternating direction method of multipliers for computing an approximate solution of the nonconvex problem, where we decompose it into two subproblems and derive closed-form solutions to them. The advantages of our method are demonstrated through extensive experiments.]]>264155415644260<![CDATA[Sparse Representation-Based Multiple Frame Video Super-Resolution]]>2627657817439<![CDATA[FSIM: A Feature Similarity Index for Image Quality Assessment]]>208237823861257<![CDATA[Learning Deep Sharable and Structural Detectors for Face Alignment]]>264166616783745<![CDATA[Single Image Super-Resolution Using Global Regression Based on Multiple Local Linear Mappings]]>263130013143336<![CDATA[A Completed Modeling of Local Binary Pattern Operator for Texture Classification]]>19616571663304<![CDATA[Super-Resolution Person Re-Identification With Semi-Coupled Low-Rank Discriminant Dictionary Learning]]>2L) approach for SR person re-identification task. With the HR and LR dictionary pair and mapping matrices learned from the features of HR and LR training images, SLD^{2}L can convert the features of the LR probe images into HR features. To ensure that the converted features have favorable discriminative capability and the learned dictionaries can well characterize intrinsic feature spaces of the HR and LR images, we design a discriminant term and a low-rank regularization term for SLD^{2}L. Moreover, considering that low resolution results in different degrees of loss for different types of visual appearance features, we propose a multi-view SLD^{2}L (MVSLD^{2}L) approach, which can learn the type-specific dictionary pair and mappings for each type of feature. Experimental results on multiple publicly available data sets demonstrate the effectiveness of our proposed approaches for the SR person re-identification task.]]>263136313784319<![CDATA[Learning Bases of Activity for Facial Expression Recognition]]>264196519783392<![CDATA[Robust Nuclear Norm-Based Matrix Regression With Applications to Robust Face Recognition]]> -norm or -norm, which overlook the 2D structure of the error image. Recently, the nuclear norm-based matrix regression model is proposed to characterize low-rank structure of the error image. However, the nuclear norm cannot accurately describe the low-rank structural noise when the incoherence assumptions on the singular values does not hold, since it overpenalizes several much larger singular values. To address this problem, this paper presents the robust nuclear norm to characterize the structural error image and then extends it to deal with the mixed noise. The majorization–minimization (MM) method is applied to derive a iterative scheme for minimization of the robust nuclear norm optimization problem. Then, an efficiently alternating direction method of multipliers (ADMM) method is used to solve the proposed models. We use weighted nuclear norm as classification criterion to obtain the final recognition results. Experiments on several public face databases demonstrate the effectiveness of our models in handling with variations of structural noise (occlusion, illumination, and so on) and mixed noise.]]>265228622953887<![CDATA[Blind Image Blur Estimation via Deep Learning]]>254191019214347<![CDATA[DehazeNet: An End-to-End System for Single Image Haze Removal]]>2511518751985832<![CDATA[Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization]]>l_{1}-norm optimization techniques and the fact that natural images are intrinsically sparse in some domains. The image restoration quality largely depends on whether the employed sparse domain can represent well the underlying image. Considering that the contents can vary significantly across different images or different patches in a single image, we propose to learn various sets of bases from a precollected dataset of example image patches, and then, for a given patch to be processed, one set of bases are adaptively selected to characterize the local sparse domain. We further introduce two adaptive regularization terms into the sparse representation framework. First, a set of autoregressive (AR) models are learned from the dataset of example image patches. The best fitted AR models to a given patch are adaptively selected to regularize the image local structures. Second, the image nonlocal self-similarity is introduced as another regularization term. In addition, the sparsity regularization parameter is adaptively estimated for better image restoration performance. Extensive experiments on image deblurring and super-resolution validate that by using adaptive sparse domain selection and adaptive regularization, the proposed method achieves much better results than many state-of-the-art algorithms in terms of both PSNR and visual perception.]]>207183818575031<![CDATA[Pairwise Operator Learning for Patch-Based Single-Image Super-Resolution]]>26299410032922<![CDATA[The contourlet transform: an efficient directional multiresolution image representation]]>1412209121061511<![CDATA[Image change detection algorithms: a systematic survey]]>1432943071340<![CDATA[Detail-Enhanced Multi-Scale Exposure Fusion]]>263124312527713<![CDATA[Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry]]>2512553855513629<![CDATA[FRESH—FRI-Based Single-Image Super-Resolution Algorithm]]>258372337357200<![CDATA[Bounded Self-Weights Estimation Method for Non-Local Means Image Denoising Using Minimax Estimators]]>264163716495126<![CDATA[Robust Neighborhood Preserving Projection by Nuclear/L2,1-Norm Regularization for Image Feature Extraction]]>264160716224093<![CDATA[Depth Map Super-Resolution Considering View Synthesis Quality]]>264173217459619<![CDATA[Data-Driven Affine Deformation Estimation and Correction in Cone Beam Computed Tomography]]>263144114515593<![CDATA[Spatio-Temporal Closed-Loop Object Detection]]>263125312634333