Ultrasound image restoration based on a learned dictionary and a higher-order MRF

The restoration of images degraded by blur and multiplicative noise is a critical preprocessing step in medical ultrasound images which exhibit clinical diagnostic features of interest. This paper proposes a novel non-smooth non-convex variational model for ultrasound images denoising and deblurring motivated by the successes of sparse representation of images and FoE based approaches. Dictionaries are well adapted to textures and extended to arbitrary image sizes by defining a global image prior, while FoE image prior explicitly characterizes the statistics properties of natural image. Following these ideas, the new model is composed of the data-fidelity term, the sparse and redundant representations via learned dictionaries, and the FoE image prior model. The iPiano algorithm can efficiently deal with this optimization problem. The new proposed model is applied to several simulated images and real ultrasound images. The experimental results of denoising and deblurring show that proposed method gives a better visual effect by efficiently removing noise and preserving details well compared with two state-of-the-art methods.     

Multiplicative noise removal via combining total variation and wavelet frame

Total variation (TV) regularization has been proved effective for cartoon images restoration however it produces staircase effects, and properly wavelet frames were confirmed to provide a more smoothing approximation to the original image. In this paper, a new model for multiplicative noise removal was proposed, which combines wavelet frame-based regularization and TV regularization. A modified proximal linearized alternating direction method is developed to solve the proposed model, considering that adding a new regularization term to the TV model would yield more parameters, which will result in computational difficulties. For the new model, the existence of solution and the convergence property of the proposed algorithm are proved. Numerical experiments have proved that the proposed model has a superior performance in terms of the peak signal-to-noise ratio and the relative error values for non-piecewise constant images when compared with some state-of-the-art multiplicative noise removal models.     

基于前向后向算子分裂的稀疏性正则化图像超分辨率算法

提出了一种新的基于稀疏表示正则化的多帧图像超分辨凸变分模型, 模型中的正则项刻画了理想图 像在框架系统下的稀疏性先验, 保真项度量其在退化模型下与观测信号的一致性, 同时分析了最优解条件. 进一步, 基于前向后向算子分裂法提出了求解该模型的不动点迭代数值算法, 每一次迭代分解为仅对保真项的前向(显式)步与仅对正则项的后向(隐式)步, 从而大幅度降低了计算复杂性; 分析了算法的收敛性, 并采取序贯策略提高收敛速度. 针对可见光与红外图像序列进行了数值仿真, 实验结果验证了本文模型与数值算法的有效性.     

基于截断核范数低秩分解的自适应字典学习算法

针对过完备字典直接对图像进行稀疏表示不能很好地剔除高频噪声的影响,压缩感知后图像重构质量不高的问题,提出了基于截断核范数低秩分解的自适应字典学习算法。该算法首先利用截断核范数正则化低秩分解模型对图像矩阵低秩分解得到低秩部分和稀疏部分,其中低秩部分保留了图像的主要信息,稀疏部分主要包含高频噪声及部分物体轮廓信息;然后对图像低秩部分进行分块,依据图像块纹理复杂度对图像块进行分类;最后使用K奇异值分解（K-single value decomposition, K-SVD）字典学习算法,针对不同类别训练出多个不同大小的过完备字典。仿真结果表明,本文所提算法能够对图像进行较好的稀疏表示,并在很好地保持图像块特征一致性的同时显著提升图像重构质量。     

稀疏性正则化的图像泊松恢复模型及分裂Bregman迭代算法

生物医学、天文等成像系统通常会受到泊松噪声的干扰, 基于图像在过完备字典下的稀疏表示, 在贝叶斯最大后验概率估计框架下, 建立了针对泊松噪声的稀疏性正则化图像恢复凸变分模型, 采用负log的泊松似然函数作为数据保真项, 模型中非光滑的正则项约束图像表示系数的稀疏性, 并附加恢复图像的非负性约束. 进一步, 基于分裂Bregman方法, 提出了求解该模型的多步迭代快速算法, 通过引入辅助变量与Bregman距离, 可将原问题转化为两个简单子问题的迭代求解, 大幅度降低了计算复杂性. 实验结果验证了本文模型与数值算法的有效性.     

基于稀疏正则化和变量分裂的图像去模糊

传统的图像去模糊方法易产生振铃和边缘模糊等“伪像”效应,针对这一问题,采用非光滑的正则项约束图像在稀疏字典下表示系数的稀疏性,并引入非负约束项,提出了图像的稀疏正则化去模糊模型。进一步,基于交替方向拉格朗日乘子算法,提出了求解该模型的多变量分裂迭代快速算法,将复杂问题求解转化为三个简单子问题的迭代求解,降低了模型求解的复杂性。实验结果表明,所提出的去模糊模型及其快速算法相对较好地保持了图像的结构特征和平滑性,并降低了计算复杂性。     

Denoising for Multiple Image Copies through Joint Sparse Representation

This paper addresses the recovery of original images from multiple copies corrupted with the noises, which can be represented sparsely in some dictionary. Sparse representation has been proven to have strong ability to denoise. However, it performs suboptimally when the noise is sparse in some dictionary. A novel joint sparse representation (JSR)-based image denoising method is proposed. The images can be recovered well from multiple noisy copies. All copies share a common component—the image, while each individual measurement contains an innovation component—the noise. Our method can separate the common and innovation components, and reconstruct the images with the sparse coefficients and the dictionaries. Experiment results show that the performance of the proposed method is better than that of other methods in terms of the metric and the visual quality.     

结合全变差与自适应低秩正则化的图像压缩感知重构

针对基于固定变换基的协同稀疏图像压缩感知(CS)重构算法不能充分利用图像自相似特性的问题,提出了一种改进的联合全变差与自适应低秩正则化的压缩感知重构方法。首先,通过图像块匹配法寻找结构相似块,并组成非局部相似块组;然后,以非局部相似块组加权低秩逼近替代协同稀疏表示中的三维小波变换域滤波;最后,结合梯度稀疏与非局部相似块组低秩先验构成重构模型的正则化项,并采用交替方向乘子法求解实现图像重构。实验结果表明,相比协同稀疏压缩感知重构(RCoS)算法,该方法重构图像的峰值信噪比平均可提升约2 dB,所提算法在准确描述图像非局部自相似结构特征的前提下显著提高了重构质量,更好地保留了图像的纹理细节信息。     

基于L1/2正则化的超分辨率图像重建算法

为提高图像重建质量,研究超分辨率图像重建技术与稀疏表示理论,提出一种基于L1/2正则化的超分辨率图像重建算法.将L1/2正则化理论运用到字典学习中,利用学习得到的字典重建高分辨率图像.实验结果表明,该算法的图像重建效果优于基于L1正则化的超分辨率图像重建算法.     

基于Moreau-包络的近似平滑迭代磁共振图像重建算法

针对基于压缩感知（CS）的磁共振成像（MRI）稀疏重建中存在的两个非平滑正则项问题,提出了一种基于Moreau包络的近似平滑迭代算法（PSIA）。基于CS的经典MRI稀疏重建是求解一个由最小二乘保真项、小波变换稀疏正则项和总变分（TV）正则项线性组合成的目标函数最小化问题。首先,对目标函数中的小波变换正则项作平滑近似;然后,将数据保真项与平滑近似后的小波正则项的线性组合看成一个新的可以连续求导的凸函数;最后,采用PSIA对新的优化问题进行求解。该算法不仅可以同时处理优化问题中的两个正则约束项,还避免了固定权重带来的算法鲁棒性问题。仿真得到的体模图像及真实磁共振图像的实验结果表明,所提算法与四种经典的稀疏重建算法：共轭梯度（CG）下降算法、TV1范数压缩MRI（TVCMRI）算法、部分k空间重建算法（RecPF）和快速复合分离算法（FCSA）相比,在图像信噪比、相对误差和结构相似性指数上具有更好的重建结果,且在算法复杂度上与现有最快重建算法即FCSA相当。     

Joint weighted nuclear norm and total variation regularization for hyperspectral image denoising

A hyperspectral image is typically corrupted by multiple types of noise including Gaussian noise and impulse noise. On the other hand, a hyperspectral image possesses a high correlation in its spectral dimensions, and its Casorati matrix has a very low rank. Inspired by the recent development of robust principal component analysis, which can be used to remove sparse and arbitrarily large noise from a low-rank matrix, we propose a joint weighted nuclear norm and total variation regularization method to denoise a hyperspectral image data. First, weighted nuclear norm regularization is constructed for sparse noise removal. Total variation regularization is then imposed on each band of the hyperspectral image to further remove the Gaussian noise. A concrete optimization algorithm is developed to implement the two-stage regularization. The combined approach is expected to effectively denoise hyperspectral images even with varying data structures and under varying imaging conditions. Extensive experiments on both simulated and real data sets validate the performance of our proposed method.     

基于带补偿字典的松弛稀疏表示的小样本人脸识别*

在训练集类内变化类型不可控的小样本人脸识别问题中,补偿字典很难发挥足够作用。在基于带补偿字典的稀疏表示的人脸识别方法中,训练集字典和补偿字典对测试图片表示的能力不同,文中讨论因此不同而导致的二者在稀疏性上的不同要求,通过对两类字典采用不同的稀疏性约束,提出基于带补偿字典的松弛稀疏表示的人脸识别方法。实验表明,在训练集图片类内变化类型不可控的小样本人脸识别问题中,文中方法能取得较优效果。     

A fast minimization method for blur and multiplicative noise removal

Multiplicative noise and blur removal problems have attracted much attention in recent years. In this paper, we propose an efficient minimization method to recover images from input blurred and multiplicative noisy images. In the proposed algorithm, we make use of the logarithm to transform blurring and multiplicative noise problems into additive image degradation problems, and then employ l ₁-norm to measure in the data-fitting term and the total variation to measure the regularization term. The alternating direction method of multipliers (ADMM) is used to solve the corresponding minimization problem. In order to guarantee the convergence of the ADMM algorithm, we approximate the associated nonconvex domain of the minimization problem by a convex domain. Experimental results are given to demonstrate that the proposed algorithm performs better than the other existing methods in terms of speed and peak signal noise ratio.     

基于稀疏特征迁移的语音情感识别

为了解决语音情感识别系统中训练数据和测试数据来自不同数据 库所引起的识别率降低的问题,提出了一种基于稀疏特征迁移的语音情感识别方法。通过引入稀疏编码获取情感特征在不同数据库条件下的共同稀疏表示;同时引入最大区分差异（Maximum mean discrepancy, MMD）来衡量不同数据库条件下稀疏表示分布之间的距离,并将其作为稀疏编码目标函数的约束条件,从而获得较为鲁棒的稀疏特征。实验结果表明,相比传统语音情感识别方法,基于稀疏特征迁移的语音情感识别方法显著提高了跨库条件下的情感识别率。     

基于稀疏表示与非局部相似的图像去噪算法

针对受加性高斯白噪声(AWGN)与椒盐噪声(SPIN)以及随机值冲击噪声(RVIN)组成的混合噪声污染的图像进行去噪的问题,提出一种在现有加权编码算法的基础上将图像稀疏表示和非局部相似先验融合的改进算法。首先,利用基于字典的图像稀疏表示构建去噪变分模型,对模型中的数据保真项设计一个权重因子来抑制冲击噪声的干扰;其次,利用非局部平均思想对混合噪声图像进行初始去噪,在得到的图像中构建掩膜矩阵将冲击噪声点排除进而求取非局部相似先验知识;最后,将非局部相似先验与稀疏先验融合进变分模型的正则项中,求解变分模型得到最终去噪图像。实验结果表明,在不同的噪声比率下,所提算法与模糊加权非局部平均算法相比,峰值信噪比(PSNR)提高了1.7 dB,特征相似性指数(FSIM)提高了0.06;与加权编码算法相比,PSNR提高了0.64 dB,FSIM提高了0.03。该算法对于纹理较强的图像可以显著提升去噪效果,能有效地保留图像的本真信息。     

一种基于非局部思想的改进图像降噪算法

数字图像因噪声的影响会严重降低其视觉效果,图像降噪算法的研究是数字图像处理领域的一个重要研究方向。本文在基于稀疏和冗余字典的图像降噪算法基础上,提出了一种基于非局部思想的改进图像降噪算法。与传统的基于稀疏表达的图像降噪算法KSVD相比,本文算法增加了一个相似块聚合的过程,使得学习的字典更小且更准确。利用自然图像包含很多的自相似,相似样本聚合学习出的字典比传统KSVD算法能更准确更稀疏的表示样本。稀疏度的提高使得重建后的信号更加的准确,适应性更好。实验证明本文算法取得了更好的视觉效果。     

自适应步长非局部全变分约束迭代图像重建算法

针对计算机断层成像（CT）系统中,全变分（TV）迭代约束模型易于产生阶梯效应以及不能很好地保存图像中精细结构的问题,提出一种自适应步长的非局部全变分（NLTV）约束迭代重建算法。考虑到NLTV模型能较好保存和恢复图像细节以及纹理的特点,首先将CT模型当成在满足投影数据的保真项的解集中寻找满足特定正则项即NLTV最小化的解约束优化模型;然后,使用代数重建（ART）算法和分离布雷格曼（SB）来确保重建结果满足数据保真项和正则化项的约束;最后,以自适应最速下降-投影到凸集（ASD-POCS）算法作为基础迭代框架来重建图像。实验结果表明,在不含噪声的稀疏重建条件下,提出的算法使用30个角度的投影数据已经可以重建出理想的结果。在含噪稀疏数据重建实验中,该算法在30次迭代时已得到接近最终收敛的结果,且均方根误差（RMSE）是ASD-POCS算法的2.5倍。该重建算法能在稀疏投影数据下重建出精确的结果图像,同时改善了TV迭代模型的细节重建能力,且对噪声有一定的抑制作用。     

基于字典学习和拓展联合动态稀疏表示的SAR目标识别

提出了一种基于字典学习和拓展联合动态稀疏表示的合成孔径雷达(Synthetic aperture radar, SAR)图像的目标自动识别(Automatic target recognition, ATR)方法.首先, 在图像预处理时, 分割出目标区域和目标遮挡地面形成的阴影区域, 将这两个区域的信息结合起来能更好地表示图像.其次, 将字典学习方法LC-KSVD (Label consistent k-singular value decomposition)引入到训练阶段中, 分别学习目标区域和阴影区域的特征字典, 而不是直接将所有训练样本作为固定字典.最后, 在测试阶段提出了拓展联合动态稀疏表示算法, 使图像数据中的两个特征共享相似但不完全相同的稀疏模式, 还可处理图像噪声遮挡损坏问题.标准数据集上的实验结果表明, 该方法使不同类别更具区分性, 有效地提高了SAR图像的目标识别准确度.     

基于压缩感知的超分辨率图像重建

压缩感知(CS)利用图像稀疏表示的先验知识,从少量的观测值中重建出原始图像。将CS理论应用于单幅图像超分辨率(SR),提出一种基于两步迭代收缩算法和全变分(TV)稀疏表示的图像重建方法。该方法无需任何训练集,仅需单幅低分辨率实现图像重建。算法在测量矩阵里加入下采样低通滤波器以使SR问题满足应用CS理论的有限等距性质;采用TV正则化函数,利用两步迭代法引入TV去噪算子,可以更好地重建图像边缘。实验结果证明,与已有的超分辨率方法相比,在不同的放大倍数下所提方法重建图像视觉效果更好,在峰值信噪比(PSNR)的评价指标上有显著的提高(4~6dB),且实验证实滤波器的引入决定算法的重建质量。     

Texture image prior for SAR image super resolution based on total variation regularization using split Bregman iteration

In this article, we propose a total variation (TV) regularization approach for the reconstruction of super-resolution synthetic aperture radar (SAR) image based on gradient profile prior or other texture image prior in the maximum a posteriori framework. We also design a novel super-resolution reconstruction algorithm via split Bregman iteration with the known degradation matrix, thereby enhancing the resolution of the SAR image. The parameter adaptation of the TV regularization is performed based on the high-resolution (HR) SAR image at each step. Several evaluation indices are tested on SAR images for objective assessment of the performance of SAR image super-resolution reconstruction. This computationally efficient algorithm is robust to noise in SAR scenes in HR image estimation. Experimental results show that the proposed split Bregman super-resolution approach can effectively avoid the speckle noise generated due to some strange textures and has good effect of noise suppression, while effectively maintaining the SAR image content, the structure of the SAR image is more apparent. Additionally, the experimental results on real SAR scenes also demonstrate the effectiveness of the proposed algorithm and demonstrate its superiority to other super-resolution algorithms.