超声图象的自适应线边界检测方法

针对超声图象存在一种特殊的斑点噪声 ,使图象边界与细节变得模糊 ,而严重影响图象质量的问题 ,提出了一种自适应线边界检测方法 ,即以不同方向与不同大小的“窄条”来近似组织边界 ,这种“窄条”是指具有不同长度、方向各异的线段 .该方法首先将经过每一像素点的“窄条”的最大投影作为该点的灰度值 ;然后应用假设试验优化方法确定“窄条”方向 ,而“窄条”的长度由基于区域增长的局部统计特性决定 .通过引入噪声抑制与边缘保留量化参数 ,进行了仿真斑点图与组织超声图的处理实验 ,并与自适应斑点抑制滤波、直接线边界检测方法进行了比较 ,结果证明 ,该方法不但能有效地抑制斑点噪声、而且能很好地保留与增强图中的组织边界与局部细节 .     

引入欧氏距离的各向异性扩散相干斑抑制

目的 相干斑噪声严重影响SAR影像解译。抑制相干斑同时,获取较好的边缘保持效果始终是相干斑抑制的重点。针对该问题,提出一种引入欧氏距离的各向异性扩散（EDAD）相干斑抑制方法。方法 EDAD算法以P-M模型与SRAD算法为基础,利用邻近像素间区域欧氏距离代替原有边缘检测算子,自适应区分同质区与异质区,有效构造各向异性扩散系数,完成相干斑抑制。结果 运用EDAD算法与现存各向异性扩散算法对截取的两景TanDEM-X影像进行试验研究并比较各类算法的评估参数。EDAD算法的等效视数分别为3.996与5.859,均高于其他算法,体现优越的相干斑抑制能力;EDAD算法相干斑抑制前后比值影像的均值分别为0.999与1.001,方差分别为0.270与0.269,较其他算法均更接近理想值1与0.273,展现更优边缘保持与相干斑抑制能力。结论 本文算法可有效提高边缘检测能力,获取更优相干斑抑制效果。经验证,对分布较散的弱相干斑区域与分布较集中的强相干斑区域均有较好适用性。     

基于偏微分方程的医学超声图像去噪方法

研究了各向异性扩散方程在医学超声图像去噪中的应用。在理论上对去噪原理进行了分析,并在此基础上采用改进的针对乘性噪声的各向异性扩散算法对医学超声图像去噪,实验结果表明,该方法在有效去除噪声的同时较好地保留了医学超声图像中的重要细节信息,使图像的细节部分清晰。该方法可以有效地去除超声图像斑纹噪声,提高图像的质量。     

Ultrasound speckle reduction by a SUSAN-controlled anisotropic diffusion method

An ultrasound speckle reduction method is proposed in this paper. The filter, which enhances the power of anisotropic diffusion with the Smallest Univalue Segment Assimilating Nucleus (SUSAN) edge detector, is referred to as the SUSAN-controlled anisotropic diffusion (SUSAN_AD). The SUSAN edge detector finds image features by using local information from a pseudo-global perspective. Thanks to the noise insensitivity and structure preservation properties of SUSAN, a better control can be provided to the subsequent diffusion process. To enhance the adaptability of the SUSAN_AD, the parameters of the SUSAN edge detector are calculated based on the statistics of a fully formed speckle (FFS) region. Different FFS estimation schemes are proposed for envelope-detected speckle images and log-compressed ultrasonic images. Adaptive diffusion threshold estimation and automatic diffusion termination criterion are employed to enhance the robustness of the method. Both synthetic and real ultrasound images are used to evaluate the proposed method. The performance of the SUSAN_AD is compared with four other existing speckle reduction methods. It is shown that the proposed method is superior to other methods in both noise reduction and detail preservation.     

基于各向异性扩散的图像平滑及在三维重构预处理中的应用

采用基于各向异性扩散的偏微分方程，其初始值为输入图像，转化为差分格式迭代求解滤波结果。在去除噪声的同时，保持重要的边缘和局部细节。在此基础上提出了8向的各向异性扩散和边缘增强的处理技术，取得了满意的结果，并将此切片图像经聚类分群运用到三维重构中，使重构的效果更好。     

PolSAR anisotropic diffusion filter with a refined similarity measure and an adaptive fidelity constraint

The presence of speckle complicates the tasks of interpreting and analysing polarimetric synthetic aperture radar (PolSAR) images. The nonlinear anisotropic diffusion (AD) method has been found to perform well in removing image noise. In this article, we propose a new AD method for PolSAR speckle reduction. An iterative refinement method is employed to measure the similarity between pixels and construct the diffusion coefficient in the iteration process, by considering both information in the original speckled image and the restored image of the last iteration. In addition, to alleviate the over-smoothing problem the conventional AD methods often encounter, an adaptive fidelity constraint is added into the diffusion equation by considering local heterogeneity information and the amount of noise. Experiments on both simulated and real PolSAR images confirm the ability of the proposed method to both suppress speckle and retain image details.     

An improved speckle-reduction algorithm for SAR images based on anisotropic diffusion

This paper mainly studies the algorithm of anisotropic diffusion for speckle noise removal of SAR images. Because the Gauss curvature driven diffusion method is sensitive to the noise and is of low efficiency on suppressing the speckle noise, an improved denoising algorithm is proposed. The new algorithm introduces the difference curvature as the diffusion coefficients of the function, which solves the problem that Gauss curvature driven diffusion is sensitive to the speckle noise, further, Tukey’s biweight function is used to control the curvature diffusion model, which can not only better protect edges, but also automatically control the diffusion. Numerical experiments show that the improved algorithm can preserve the information of textures, edges while inhibiting the speckle of SAR images.     

改进的P-M扩散方程在相干斑抑制中的应用

直接基于Perona-Malik扩散方程的滤波算法对于加性噪声非常有效,但是对于乘性噪声（如合成孔径雷达（SAR）图像相干斑噪声）收效甚微。提出了一种基于改进的Perona-Malik扩散方程抑制SAR图像相干斑噪声的新算法。分析对数变化对相干斑噪声的影响,为将P-M扩散方程应用于相干斑噪声抑制奠定了理论基础;通过P-M扩散和稳健统计学的联系,建立了基于Biweight Estimator误差模型的扩散系数;同时利用非线性衰减技术对梯度阈值的选择改进。实验表明,该方法不仅有效抑制了SAR图像相干斑噪声,较好地保持了细节和边缘信息,而且视觉效果比较好。     

Speckle reduction of ultrasound images based on Rayleigh-trimmed anisotropic diffusion filter

A novel method is proposed to reduce speckle in ultrasound images. Based on the assumption of Rayleigh distribution of speckle, a Rayleigh-trimmed filter is first proposed to estimate the relative standard deviations of local signals and the results are used to determine the parameter that controls an alpha-trimmed mean filter for suppressing the primary noise. Then the anisotropic diffusion is subsequently applied to further reduce noise while enhancing features and structures in the original image. We also extend the proposed method to three-dimensional space by introducing time as one additional dimension. The proposed method effectively utilizes the statistical characteristics of speckle and the two-step despeckling algorithm reduces speckle significantly while retaining important features. The effectiveness of the proposed method is well demonstrated by experiments on both simulated and real ultrasound images.     

一种新的边缘保留各向异性扩散方法

由于超声图像中的斑点严重影响了图像质量,也增加了临床诊断与治疗的困难,因此对于噪声图像,往往要先用高斯卷积对图像进行一定的平滑,再通过求微分来检测边缘。为了更好地滤除超声图像中的斑点,通过构造基于高斯卷积的结构张量,并将其引入到各向异性扩散方法中,实验结果表明,这种新的各向异性扩散方法不仅能有效地抑制斑点噪声,而且能检测并保留图像边缘与细节特征。     

A segmentation algorithm for SAR images based on the anisotropic heat diffusion equation

A method toward unsupervised segmentation of synthetic aperture radar (SAR) images is proposed. In this method, the distribution of SAR intensity image and the maximum a posteriori (MAP) algorithm is used to obtain an initial segmentation. Then according to the equivalence between the solid heat diffusion model and image scale-space, multiscale anisotropic smoothing of the posterior probability matrixes is introduced to remove the influence of speckle and to preserve important structure information. The effectiveness of this algorithm is demonstrated by application to simulated and real SAR images.     

一种基于小波域隐马尔可夫模型的SAR相干斑抑制算法

相干斑噪声是SAR图像的固有特点。对相干斑抑制的要求是在平滑噪声的同时，尽量保持原始图像的结构信息。现有的许多相干斑抑制方法各有优点和不足，没有普遍的适用性。基于图像在小波域的隐马尔可夫模型(HMMs)结构，结合SAR图像中相干斑噪声的统计特性，本文提出了一种新的小波域相干斑抑制方法。仿真及实测数据处理结果表明，该方法在有效抑制相干斑的同时，更好地保持了边缘结构。与小波域软阈值去噪方法和Lee滤波器相比较，该方法在噪声平滑及边缘保持上都取得了较大的改进，并得到了较好的视觉效果。     

基于异性扩散-中值滤波的超声医学图像去噪方法

针对超声图像存在一种特殊的斑点噪声,使图像边界与细节变得模糊而严重影响图像质量的问题,提出了一种新的去除医学图像斑点噪声的方法,它利用中值滤波和各向异性扩散相结合,不仅可以有效地去除噪声而且很好地保持了边缘、局部细节信息.此外,该方法在扩散过程中,梯度阈值选取的不同对图像结果影响很小,这极大地提高了该算法的健壮性.实验中,通过和各向异性扩散、中值滤波等方法的比较,表明该方法具有良好的去噪效果.     

相干光学系统图像复原的各向异性扩散方法

相干光学系统中图像噪声污染严重,提出一种基于各向异性扩散的图像复原模型,该模型的扩散系数从理论上满足Charbonnier等人提出的构造扩散系数准则,同时结合对数变换对相干光学图像进行复原去噪处理。实验结果表明,同SRAD、Lee、Frost、Non-local Means算法和基于小波的BLS-GSM、BM3D等方法相比,该算法可以更有效地进行边缘平滑,而且还能够较好地解决图像边缘和细节失真的问题,不论从PSNR,还是从视觉评价效果来看,该算法都具有一定的优越性。     

Speckle Reduction with Trained Nonlinear Diffusion Filtering

Speckle reduction is a prerequisite for many image processing tasks in synthetic aperture radar images, as well as all coherent images. In recent years, predominant state-of-the-art approaches for despeckling are usually based on nonlocal methods which mainly concentrate on achieving utmost image restoration quality, with relatively low computational efficiency. Therefore, in this study we aim to propose an efficient despeckling model with both high computational efficiency and high recovery quality. To this end, we exploit a newly developed trainable nonlinear reaction diffusion (TNRD) framework which has proven a simple and effective model for various image restoration problems. In the original TNRD applications, the diffusion network is usually derived based on the direct gradient descent scheme. However, this approach will encounter some problem for the task of multiplicative noise reduction exploited in this study. To solve this problem, we employed a new architecture derived from the proximal gradient descent method. Taking into account the speckle noise statistics, the diffusion process for the despeckling task is derived. We then retrain all the model parameters in the presence of speckle noise. Finally, optimized nonlinear diffusion filtering models are obtained, which are specialized for despeckling with various noise levels. Experimental results substantiate that the trained filtering models provide comparable or even better results than state-of-the-art nonlocal approaches. Meanwhile, our proposed model merely contains convolution of linear filters with an image, which offers high-level parallelism on GPUs. As a consequence, for images of size \(512 \times 512\), our GPU implementation takes less than 0.1 s to produce state-of-the-art despeckling performance.     

基于数据融合及小波变换的医学超声图像去噪方法

医学超声图像固有的斑纹噪声,极大地降低了超声图像的质量,严重影响了对病灶的识别。经典的去噪方法在抑制斑纹噪声时丢失了图像中大量的细节和微弱的边缘信息。本文提出一种基于数据融合的小波变换去噪算法,首先对医学超声图像进行对数变换,将乘性噪声变成加性噪声,然后对同一原始信号含噪声的两幅同源图像分别进行小波分解,对两幅图像中小波系数的低频分量作加权融合;对水平、垂直与对角方向高频分量取两幅图像中各尺度下对应小波系数绝对值较大者各自分别融合,使高频分量中信号得以最大限度地保留,最后,经小波逆变换和指数变换得到去噪后图像。该方法在去除噪声同时能够有效保持边缘信息,较好地改善去噪后图像的视觉效果,取得了良好的效果。     

用于超声斑点噪声滤波的各向异性扩散新模型

由于扩散系数的缺点,原斑点噪声各向异性扩散模型(Speckle reducing anisotropic diffusion, SRAD)有产生板块效应、模糊弱边界与细节等缺点. 本文通过改进扩散系数,提出一种新的斑点噪声各项异性扩散模型(New speckle reducing anisotropic diffuse, NSRAD), NSRAD中采用一个S型函数作为扩散系数:在同质区域中,采用各向同性扩散, 避免了板块效应; 在结构性区域中,扩散速度变化敏感,同时以更快趋向于0的速度扩散,因此,提高了该区域的分辨率,达到增强细节和弱边界以及保留边界的锐利性的目的. 仿真图像的定量分析证明新方法不仅比原SRAD除噪更有效,而且提高了除噪后图像与原图像的结构相似性,同时具有更小形变. 真实图像的试验结果也证明新方法在有效除噪的同时消除了黑板刷效应,增强了边界以及细节.     

基于结构重参数化的太阳斑点图像弱监督去模糊方法

针对云南天文台拍摄的模糊太阳斑点图像使用有监督学习模型进行重建时容易产生伪像、训练时间长、重建结果过分依赖参考图像等问题,提出一种基于结构重参数化与多分支模块相结合的弱监督去模糊方法重建太阳斑点图。首先,结合单尺度与多尺度网络设计去模糊模型,在模型中构造多分支模块提取不同尺度的特征,增强细节信息,减少伪像生成;其次,对每个分支结构进行重参数化,使得结构参数的重用贯穿整个特征提取过程,节省计算时间;之后,将去模糊模型分别嵌入退化学习与逆退化学习的弱监督训练中,先对模糊图像进行等级划分,利用退化模型分别学习不同等级的退化,构成对应等级的配对数据集,再使用去模糊模型对数据集进行逆退化,实现太阳斑点图的重建。实验结果表明,该方法与现有深度学习去模糊方法相比,模型训练效率更高,对参考图像的依赖较小,能够满足太阳斑点图像高分辨率重建要求。     

基于生成对抗网络的梯度引导太阳斑点图像去模糊方法

针对云南天文台拍摄的高度模糊的太阳斑点图像采用现有深度学习算法恢复难度大、高频信息难以重建等问题,提出了一种基于生成对抗网络（GAN）与梯度信息联合的去模糊方法来重建太阳斑点图,并很好地恢复出图像的高频信息。该方法由一个生成器与两个鉴别器构成：首先,生成器采用特征金字塔网络（FPN）框架来获取图像多尺度特征,再将这些特征分层次输入梯度分支以梯度图的形式捕获更小的局部特征;然后,联合梯度分支结果与FPN结果共同重建出具有高频信息的太阳斑点图像;其次,在常规对抗鉴别器的基础上,增加了一个鉴别器用于保证由梯度分支产生的梯度图更加真实;最后,引入一个包括像素内容损失、感知损失和对抗损失的联合训练损失来引导模型进行太阳斑点图像高分辨率重建。实验结果表明,进行图像预处理后的所提方法与现有的深度学习去模糊方法相比,高频信息恢复能力更强,峰值信噪比（PSNR）和结构相似性（SSIM）指标均有显著提高,分别达到27.801 0 dB与0.851 0,能够满足太阳观测图像高分辨率重建的需要。     

Speckle filtering in satellite SAR change detection imagery

Repeat-pass Synthetic Aperture Radar (SAR) imagery is useful for change detection. A disadvantage of SAR is the system-inherent speckle noise. This can be reduced by filtering. Various filter types and methods are described in the literature, but not one fits the speckle noise in change detection imagery. A new method is therefore developed in this paper. The new method is based on filtering the logarithmic-scaled ratio of SAR images. Logarithmic scaling changes the multiplicative speckle noise in the ratio-image into additive noise and alters the distribution, which simplifies and optimizes the subsequent filter process. The filter in the new method consists of an additive LLMMSE filter (Kuan et al. 1985), preceded by a structure detection stage for a better contour preserving performance. Testing the new method on a repeat-pass satellite SAR image-set gave an accurate overview of changes compared to a colour-composite of both images, other optical remote sensing images and maps of the same area.