Joint sparsity and fidelity regularization for segmentation-driven CT image preprocessing基于稀疏性和保真性正则化模型的分割驱动的CT图像预处理研究

In this paper, we propose a novel segmentation-driven computed tomography (CT) image preprocessing approach. The proposed approach, namely, joint sparsity and fidelity regularization (JSFR) model can be regarded as a generalized total variation (TV) denoising model or a generalized sparse representation denoising model by adding an additional gradient fidelity regularizer and a stronger gradient sparsity regularizer. Thus, JSFR model consists of three terms: intensity fidelity term, gradient fidelity term, and gradient sparsity term. The interactions and counterbalance of these terms make JSFR model has the ability to reduce intensity inhomogeneities and improve edge ambiguities of a given image. Experimental results carried out on the real dental cone-beam CT data demonstrate the effectiveness and usefulness of JSFR model for CT image intensity homogenization, edge enhancement, as well as tissue segmentation.     

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。     

优化加权TV的复合正则化压缩感知图像重建

目的：压缩感知理论突破了传统的Shanon-Nyquist采样定理的限制,能够以较少的采样值来进行原信号的恢复。针对压缩感知图像重建问题,本文提出了一种基于优化加权全变差（Total Variation, TV）的复合正则化压缩感知图像重建模型。方法：提出的重建模型是以TV正则化模型为基础的。首先,为克服传统TV正则化会导致重建图像的边缘和纹理细节部分模糊或丢失的缺点,本文引入图像的梯度信息估计权重,构建加权TV的重建模型。其次,利用全变差去噪（Rudin–Osher–Fatemi,ROF）模型对权重进行优化估计,从而减少计算权重时受噪声的影响。再次,本文将非局部结构相似性先验和局部自回归性先验引入提出的加权TV模型,得到优化加权TV的复合正则化重建模型。最后,结合投影法和算子分裂法对优化模型求解。结果：针对自然图像的不同特性,本文使用复合正则化先验进行建模,实验表明上述重建问题通过我们的方法得到了很好的解决,加权TV正则化先验使得图像的平坦区域和强边重建较好,而非局部结构相似性先验和局部自回归性先验能够保证图像的精细结构部分的重建效果。结论：本文提出了一种新的复合正则化压缩感知重建模型。与其它基于TV正则化的重建模型相比,实验结果表明本文模型的重建性能无论是在视觉效果还是在客观评价指标上都有明显的提高。     

TH-UWB系统中基于自适应算法的接收机研究

提出了一种适用于跳时超宽带(TH-UWB)系统中的RAKE接收机方案。该方法利用基于梯度的可变遗忘因子的改进递推最小二乘(RLS)算法进行信道估计,并与基于经典RLS算法和基于最大似然概率(ML)算法的接收机方案进行对比。结果表明,这种新型RAKE接收机方案能够更有效地跟踪时变衰落信道的变化;在相同条件下,该方案能够提高系统性能,获得更小的误码率(BER)。     

鉴别性最大后验概率声学模型自适应

为了更加准确地估计最小音素错误最大后验概率(MPE-MAP)自适应算法中的先验分布中心,使自适应后的声学模型参数更为准确,从而提高系统的识别性能,分别采用最大互信息最大后验概率(MMI-MAP)自适应和基于最大互信息准则与最大似然准则相结合的H-criterion最大后验概率(H-MAP)自适应估计先验分布中心,提出了基于最大互信息最大后验概率先验的最小音素错误最大后验概率(MPE-MMI-MAP)和基于H-criterion最大后验概率先验的最小音素错误最大后验概率(MPE-H-MAP)算法。任务自适应实验结果表明,MPE-MMI-MAP和MPE-H-MAP算法的自适应性能均优于MPE-MAP、MMI-MAP和最大后验概率(MAP)自适应方法,分别比MPE-MAP相对提高3.4%和2.7%。     

Multiplicative noise removal combining a total variation regularizer and a nonconvex regularizer

A novel variational model for removing multiplicative noise is proposed in this paper. In the model, a novel regularization term is elaborately designed which is inherently equivalent to a combination of the classical total variation regularizer and a nonconvex regularizer. The proposed regularization term, on the one hand, can better remove the noise in homogeneous regions of a noisy image and, on the other hand, can preserve edge details of the image during the denoising process. In order to solve the model efficiently, we design an alternating iteration process in which two coupling minimization problems are solved. For each of the two minimization problems, the existence and uniqueness of their solutions are proved under some necessary assumptions. Numerical results are reported to demonstrate the effectiveness of the proposed regularization term for multiplicative noise removal.     

Recursive decision directed estimation of reflection coefficients for seismic data deconvolution

This paper concerns the problem of estimation of the location and intensity of reflections of a seismic wavelet. A recursive maximum a posteriori probability (MAP) algorithm is derived as an alternative to the maximum likelihood (ML) algorithm of Mendel and Kormylo. The MAP approach proposed here yields a suboptimal detector which is substantially different in details from the corresponding approximate ML detector of Mendel and Kormylo. Simulation studies are presented to show that the MAP detector performs as well as the ML detector and can yield comparable results with much less computational effort. A comparative study of both the MAP and ML detectors has been made via simulations which show some interesting differences in structure as well as performance.     

Multiplicative Denoising Based on Linearized Alternating Direction Method Using Discrepancy Function Constraint

The multiplicative noise (speckle) in coherent imaging systems such as synthetic aperture radar makes it difficult to interpret observed images. Recently, the total variation (TV) models have received much interest in removing the speckle due to the strong edge preserving ability and low computational cost of the TV regularizer. However, the classical methods have difficulties in two aspects: one is how to efficiently compute the solution of the models with special data-fidelity terms, the other is how to choose the regularization parameter since the variational models are rather sensitive to the parameter. In this paper, we propose a new linearized alternating direction method, which is able to handle the data-fidelity term efficiently, and meanwhile estimate the optimal value of the regularization parameter exactly based on a discrepancy function constraint. We further establish the global convergence of the proposed algorithm. Numerical experiments demonstrate that our methods overall outperform the current state-of-the-art methods for multiplicative noise removal.     

基于正则化方法的图像盲去模糊

针对标准化稀疏先验的正则化方法估计复杂模糊核时的不准确性, 引入图像的预处理, 提出了一种图像盲去模糊的新方法。该方法将图像盲去模糊分为三个步骤：利用双边滤波器和冲击滤波器对图像进行预处理, 使得图像的噪声降低、边缘突出, 有利于模糊核的估计; 对预处理后的图像, 利用基于标准化稀疏先验的正则化方法估计模糊核; 根据估计出的模糊核利用TV正则化方法对图像进行非盲去卷积。采用快速迭代收缩阈值算法和快速总变分图像复原算法分别求解模糊核估计模型和图像非盲去卷积模型。实验结果表明, 针对单幅模糊图像, 该方法可以估计出准确的模糊核, 对噪声具有鲁棒性, 并且提高了图像复原速度, 具有较好的图像恢复效果。     

基于四阶偏微分方程的盲图像恢复模型

由于全变分(total variation,TV)正则化方法能够很好地保持边界,因而在图像去噪和恢复中得到广泛的应用,但其一个显著的缺点就是会在恢复出来的图像中产生阶梯效应。针对此问题给出了一种基于四阶偏微分方程(PDE)的盲图像恢复模型,该模型在Chan和Wong的全变分模型的基础上,用四阶范数来代替TV范数,构造了一种新的能量泛函,消除了全变分正则化方法所产生的阶梯效应。实验结果表明,该模型能取得较好的图像恢复效果。     

基于贝叶斯估计的改进Contourlet变换的SAR图像滤波

针对小波变换和轮廓波变换在合成孔径雷达(Synthetic aperture radar, SAR)图像中去噪应用的不足,结合小波变换和轮廓波变换的优点,将小波变换与轮廓波变换相结合,提出一种改进轮廓波变换方法。首先将待处理图像进行小波变换,然后对低频子带图像进行重建,得到一个细节子带图像,然后使用方向滤波器组对其进行多方向划分。再采用贝叶斯最大后验概率估计对划分后的方向子带信号进行估计。实验结果表明此方法在抑制图像斑点噪声的同时,很好的保持了均匀区域的辐射特性,保持了图像中的边缘以及细小纹理,且没有人为畸变。此外算法的高频子带图像含有更为丰富的纹理,对于边缘特征的提取非常有益。     

基于数据滤波的带协方差重置的递推贝叶斯算法

针对传统最小二乘算法计算量大、在有色噪声干扰下估计有误差的问题,提出了一种基于滤波技术的带协方差重置的递推贝叶斯算法。该算法首先使用一个动态非线性滤波器对输入输出数据进行滤波,然后使用贝叶斯方法进行参数估计。同时,为了加快参数的收敛速度,在算法中加入了一种新型的协方差重置策略。计算量分析表明,当过程模型和噪声模型的阶数分别为6和4的时候,所提算法可以减少约62.35%的计算量。仿真结果显示,所提算法与传统最小二乘算法在采样数据长度为3000时的估计误差分别为0.771%和1.118%。因此,所提算法具有较高的计算效率,并且可以给出精度较高的参数估计值。     

基于广义变分模型的自适应图像去噪算法

通过分析全变分(TV)去噪模型的优缺点,提出了一种新的改进算法。该算法根据最大后验概率(MAP)和马尔可夫随机场(MRF)的理论,推导出一个广义变分的图像去噪模型,并对平衡正则化项和数据保真项的Lagrange乘子λ进行了自适应改进,最后采用了一种鲁棒性好和边缘保持能力强的势函数,结合梯度加权最速下降法和半点格式的数值迭代算法对自适应的广义变分去噪模型寻优求解。实验结果表明,新模型能很好地应用于图像去噪,与现有的算法相比,在峰值信噪比有所提高的同时,图像的主观视觉效果也更好。     

Input–output data filtering based recursive least squares identification for CARARMA systems

This paper uses an estimated noise transfer function to filter the input–output data and presents filtering based recursive least squares algorithms (F-RLS) for controlled autoregressive autoregressive moving average (CARARMA) systems. Through the data filtering, we obtain two identification models, one including the parameters of the system model, and the other including the parameters of the noise model. Thus, the recursive least squares method can be used to estimate the parameters of these two identification models, respectively, by replacing the unmeasurable variables in the information vectors with their estimates. The proposed F-RLS algorithm has a high computational efficiency because the dimensions of its covariance matrices become small and can generate more accurate parameter estimation compared with other existing algorithms.     

Spatial random tree grammars for modeling hierarchal structure in images with regions of arbitrary shape

We present a novel probabilistic model for the hierarchical structure of an image and its regions. We call this model spatial random tree grammars (SRTGs). We develop algorithms for the exact computation of likelihood and maximum a posteriori (MAP) estimates and the exact expectation-maximization (EM) updates for model-parameter estimation. We collectively call these algorithms the center-surround algorithm. We use the center-surround algorithm to automatically estimate the maximum likelihood (ML) parameters of SRTGs and classify images based on their likelihood and based on the MAP estimate of the associated hierarchical structure. We apply our method to the task of classifying natural images and demonstrate that the addition of hierarchical structure significantly improves upon the performance of a baseline model that lacks such structure.     

Uncertainties for recursive estimators in nonlinear state-space models, with applications to epidemiology

Consider a nonlinear dynamic system where one wishes to estimate a state vector using noisy measurements. Many algorithms have been proposed to address this problem, among them the extended Kalman filter (and its variants) and constant-gain stochastic approximation. To quantify the efficacy of these algorithms, it is necessary to describe the distribution of the state estimation error. Typically, performance has been measured by the estimation error covariance alone, which does not provide enough information to probabilistically quantify the estimation accuracy. By casting the estimation error in an autoregressive-type form, this paper addresses the broader question of the distribution of the error for a general class of recursive algorithms. We illustrate the distributional results in an epidemiological problem of disease monitoring.     

浅层CNN网络构建的噪声比例估计模型

目的 利用深度卷积神经网络（deep convolutional neural network,DCNN）构建的非开关型随机脉冲噪声（random-valued impulse noise,RVIN）降噪模型在降噪效果和执行效率上均比主流的开关型RVIN降噪算法更有优势,但在实际应用中,这类基于训练（数据驱动）的降噪模型,其性能却受制于能否对待降噪图像受噪声干扰的严重程度进行准确的测定（即存在数据依赖问题）。为此,提出了一种基于浅层卷积神经网络的快速RVIN噪声比例预测（noise ratio estimation,NRE）模型。方法 该预测模型的主要任务是检测待降噪图像中的噪声比例值并将其作为反映图像受噪声干扰严重程度的指标,依据NRE预测模型的检测结果可以自适应调用相应预先训练好的特定区间DCNN降噪模型,从而快速且高质量地完成图像降噪任务。结果 分别在10幅常用图像和50幅纹理图像两个测试集上进行测试,并与现有的主流RVIN降噪算法中的检测模块进行对比。在常用图像测试集上,本文所提出的NRE预测模型的预测准确性最高。相比于噪声比例预测精度排名第2的算法, NRE预测模型在噪声比例预测值均方根误差上低0.6% 2.4%。在50幅纹理图像测试集上,NRE模型的均方根误差波动范围最小,表明其稳定性最好。通过在1幅大小为512×512像素图像上的总体平均执行时间来比较各个算法执行效率的优劣,NRE模型执行时间仅为0.02 s。实验数据表明：所提出的NRE预测模型在受各种不同噪声比例干扰的自然图像上均可以快速而稳定地测定图像中受RVIN噪声干扰的严重程度,非盲的DCNN降噪模型与其联用后即可无缝地转化为盲降噪算法。结论 本文RVIN噪声比例预测模型在各个噪声比例下具有鲁棒的预测准确性,与基于DCNN的非开关型RVIN深度降噪模型配合使用后能妥善解决DCNN网络模型固有的数据依赖问题。     

几种矢量图像噪声去除变分模型的边缘保持比较

矢量图像噪声去除的变分模型必须考虑不同通道图像间的耦合以保持图像边缘,但所得到的模型复杂、计算效率低,且不同耦合方法对应的模型的边缘保持质量不同。本文首先设计了目前已经提出的这类变分模型的快速Split Bregman算法,然后通过大量数值实验对不同模型的边缘保持特性和计算效率进行了比较。所研究的模型分别使用LTV(layered total variation)规则项、MTV(multichannel total variation)规则项、CTV(color total variation)规则项、PA(polyakov action)规则项和RPA(reduced polyakov action)规则项。实验结果表明CTV模型对矢量图像去噪边缘保持最好,其他依次是PA模型、MTV模型、RPA模型和LTV模型;LTV模型计算效率最高,其他依次是MTV模型、RPA模型、CTV模型和PA模型。     

加强的低秩表示图像去噪算法

由于低秩表示（Low-Rank Representation,LRR）模型中核范数对非零奇异值的估计不足,所以利用参数化的非凸惩罚函数来估计非零奇异值,同时结合全变差（Total Variation,TV）范数保持图像边缘信息和加强区域平滑性的能力,通过对LRR模型中的系数矩阵施加TV范数约束,提出了一个新的图像去噪算法,并且采取交替最小化方法求解对应模型。利用图像的内在非局部自相似性先验,所提算法能够在有效发现和移除噪声的同时,增强恢复图像的结构和区域平滑性,提高图像的恢复质量。实验结果表明,与其他去噪算法相比,无论是客观评价还是视觉效果,所提算法都实现了具有竞争力的去噪表现,特别是在噪声强度较大时。     

去除乘性噪声的重加权各向异性全变差模型

恢复含乘性噪声的图像是当前图像处理的重要研究课题. 本文提出基于迭代重加权的各向异性全变差(Total variation, TV)模型. 新模型中, 假定乘性噪声服从Gamma分布. 正则项采用加权的各向异性全变差, 其中, 自适应权函数由期望最大(Expectation maximization, EM)算法得到. 新模型在有效去噪的同时, 较好地保留了图像的边缘和细节信息, 同时能够有效地抑制"阶梯效应". 数值实验验证了新模型的效果.