Improving Medical CT Image Blind Restoration Algorithm Based on Dictionary Learning by Alternating Direction Method of Multipliers

In this paper, the medical CT image blind restoration is translated into two sub problems, namely, image estimation based on dictionary learning and point spread function estimation. A blind restoration algorithm optimized by the alternating direction method of multipliers for medical CT images was proposed. At present, the existing methods of blind image restoration based on dictionary learning have the problem of low efficiency and precision. This paper aims to improve the effectiveness and accuracy of the algorithm and to improve the robustness of the algorithm. The local CT images are selected as training samples, and the K-SVD algorithm is used to construct the dictionary by iterative optimization, which is beneficial to improve the efficiency of the algorithm. Then, the orthogonal matching pursuit algorithm is employed to implement the dictionary update. Dictionary learning is accomplished by sparse representation of medical CT images. The alternating direction method of multipliers (ADMM) is used to solve the objective function and realize the local image restoration, so as to eliminate the influence of point spread function. Secondly, the local restoration image is used to estimate the point spread function, and the convex quadratic optimization method is used to solve the point spread function sub problems. Finally, the optimal estimation of point spread function is obtained by iterative method, and the global sharp image is obtained by the alternating direction method of multipliers. Experimental results show that, compared with the traditional adaptive dictionary restoration algorithm, the new algorithm improves the objective image quality metrics, such as peak signal to noise ratio, structural similarity, and universal image quality index. The new algorithm optimizes the restoration effect, improves the robustness of noise immunity and improves the computing efficiency.     

Adaptive noise smoothing filter for images with signal-dependent noise

In this paper, we consider the restoration of images with signal-dependent noise. The filter is noise smoothing and adapts to local changes in image statistics based on a nonstationary mean, nonstationary variance (NMNV) image model. For images degraded by a class of uncorrelated, signal-dependent noise without blur, the adaptive noise smoothing filter becomes a point processor and is similar to Lee's local statistics algorithm [16]. The filter is able to adapt itself to the nonstationary local image statistics in the presence of different types of signal-dependent noise. For multiplicative noise, the adaptive noise smoothing filter is a systematic derivation of Lee's algorithm with some extensions that allow different estimators for the local image variance. The advantage of the derivation is its easy extension to deal with various types of signal-dependent noise. Film-grain and Poisson signal-dependent restoration problems are also considered as examples. All the nonstationary image statistical parameters needed for the filter can be estimated from the noisy image and no a priori information about the original image is required.     

基于噪声检测的总变分去噪算法

对受高斯和脉冲混合噪声污染的数字图像去噪方法进行了研究,提出了一种基于噪声检测的自适应总变分(TV)去噪算法。提出的改进算法采用两步迭代框架实现:脉冲噪点检测和全变分图像恢复。第一步中,考虑到脉冲噪声污染的像素点不包含原图像有效信息,采用一种局部统计值,即邻域像素间的随机绝对差排序值(ROAD)估计出噪点的位置;第二步中,采用L2-TV方法进行去噪处理,并对上述过程进行迭代处理,得到去噪图像。在噪点估计过程中引入脉冲噪点水平参数,这样处理的优势在于可更准确地检测出脉冲噪点;而L2-TV去噪方法可很好地去除高斯噪声,两者结合有效地解决了TV算法存在误判图像脉冲噪声为边缘而产生假边缘的问题。与现有典型去噪方法的比较实验表明,该迭代去噪算法,即TV-ROAD算法,既能够去除混合噪声,又可以保留图像细节特征。     

Particle Swarm Optimization Based Support Vector Regression for Blind Image Restoration

This paper presents a swarm intelligence based parameter optimization of the support vector machine (SVM) for blind image restoration. In this work, SVM is used to solve a regression problem. Support vector regression (SVR) has been utilized to obtain a true mapping of images from the observed noisy blurred images. The parameters of SVR are optimized through particle swarm optimization (PSO) technique. The restoration error function has been utilized as the fitness function for PSO. The suggested scheme tries to adapt the SVM parameters depending on the type of blur and noise strength and the experimental results validate its effectiveness. The results show that the parameter optimization of the SVR model gives better performance than conventional SVR model as well as other competent schemes for blind image restoration.     

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.     

Image restoration based on camera microscanning

Common restoration techniques use a single observed image for the processing. In this work three observed degraded images obtained from camera microscanning are utilized for image restoration. It is assumed that the degraded images contain information about an original image, multiplicative interference, and additive sensor’s noise. Using captured images a set of linear or nonlinear equations and objective function are formed. By solving the system of equations with the help of an iterative algorithm, the original image can be recovered. A fast algorithm for approximated image restoration is proposed. Computer simulations results presented and discussed.     

结合感知损失与双重对抗网络的低剂量CT图像去噪

低剂量计算机断层扫描（LDCT）成像技术在医学诊断中得到广泛应用,但其斑纹噪声和非平稳条纹伪影复杂,目前多数算法仅依靠推断条件后验概率来实现图像去噪,无法应对LDCT图像噪声复杂、数据量少、先验知识缺乏的问题。提出一种结合感知损失的双重对抗网络去噪算法,以实现LDCT图像复原。该算法包含一个去噪器和一个生成器,分别从图像去噪和噪声生成2个角度来建模干净-噪声图像对的联合分布,通过联合学习使得去噪器和生成器相互指导,从而充分学习数据中的噪声信息和清晰图像信息,且学习到的去噪器可以直接用于LDCT图像修复。考虑到通过感知损失学习语义特征差异可以使去噪结果保留更多的细节和边缘信息,提出一种掩膜自监督方法,针对CT图像域训练一个语义特征提取网络用于计算感知损失。实验结果表明,与BM3D、RED-CNN、WGAN-VGG等主流去噪算法相比,该算法可以有效抑制噪声并去除伪影,最大程度地保留边缘轮廓和纹理细节,产生更符合人眼视觉特性的去噪效果,与当下LDCT图像去噪性能较好的SACNN算法相比,所提算法的PSNR和SSIM指标分别提升1.26 dB和1.8%。     

Data mining based noise diagnosis and fuzzy filter design for image processing

In image processing, both diagnosis of noise types and filter design are critical. Conventional filtering techniques for image restoration such as median filter and mean filter are not effective in many cases, such as the case lacking the information of noise types or the case having mixed noise in images. This paper develops a data mining approach for noise type diagnosis, and proposes a fuzzy filter design for enhancing the quality of noise corrupted images. The experimental results demonstrate that the proposed technique outperforms the conventional filters, particularly for dealing with the images corrupted by mixed noise with additive Gaussian noise and impulse noise.     

Impulse Noise Removal From Digital Images by a Detail-Preserving Filter Based on Type-2 Fuzzy Logic

A novel image filter based on type-2 fuzzy logic techniques is proposed for detail-preserving restoration of digital images corrupted by impulse noise. The performance of the proposed filter is evaluated for different test images corrupted at various noise densities and also compared with representative conventional as well as state-of-the-art impulse noise filters from the literature. Experimental results show that the proposed filter exhibits superior performance over the competing operators and is capable of efficiently suppressing the noise in the image while at the same time effectively preserving thin lines, edges, texture, and other useful information within the image.      

Rician noise removal from MR images using novel adapted selective non-local means filter

The reduction of rician noise from MR images without degradation of the underlying image features has attracted much attention and has a strong potential in several application domains including medical image processing. Interpretation of MR images is difficult due to their tendency to gain rician noise during acquisition. In this work, we proposed a novel selective non-local means algorithm for noise suppression of MR images while preserving the image features as much as possible. We have used morphological gradient operators that separate the image high frequency areas from smooth areas. Later, we have applied novel selective NLM filter with optimal parameter values for different frequency regions of image to remove the noise. A method of selective weight matrix is also proposed to preserve the image features against smoothing. The results of experimentation performed using proposed adapted selective filter prove the soundness of the method. We compared results with the results of many well known techniques presented in literature like NLM with optimized parameters, wavelet based de-noising and anisotropic diffusion filter and discussed the improvements achieved.     

基于卷积自编码生成式对抗网络的高分辨率破损图像修复

目的 破损图像修复是一项具有挑战性的任务,其目的是根据破损图像中已知内容对破损区域进行填充。许多基于深度学习的破损图像修复方法对大面积破损的图像修复效果欠佳,且对高分辨率破损图像修复的研究也较少。对此,本文提出基于卷积自编码生成式对抗网络(convolutional auto-encoder generative adversarial network,CAE-GAN)的修复方法。方法 通过训练生成器学习从高斯噪声到低维特征矩阵的映射关系,再将生成器生成的特征矩阵升维成高分辨率图像,搜索与待修复图像完好部分相似的生成图像,并将对应部分覆盖到破损图像上,实现高分辨率破损图像的修复。结果 通过将学习难度较大的映射关系进行拆分,降低了单个映射关系的学习难度,提升了模型训练效果,在4个数据集上对不同破损程度的512×512×3高分辨率破损图像进行修复,结果表明,本文方法成功预测了大面积缺失区域的信息。与CE(context-encoders)方法相比,本文方法在破损面积大的图像上的修复效果提升显著,峰值信噪比(peak signal to noise ratio,PSNR)和结构相似性(str...     

A two-stage filter for high density salt and pepper denoising

Image restoration is an important and interesting problem in the field of image processing because it improves the quality of input images, which facilitates postprocessing tasks. The salt-and-pepper noise has a simpler structure than other noises, such as Gaussian and Poisson noises, but is a very common type of noise caused by many electronic devices. In this article, we propose a two-stage filter to remove high-density salt-and-pepper noise on images. The range of application of the proposed denoising method goes from low-density to high-density corrupted images. In the experiments, we assessed the image quality after denoising using the peak signal-to-noise ratio and structural similarity metric. We also compared our method against other similar state-of-the-art denoising methods to prove its effectiveness for salt and pepper noise removal. From the findings, one can conclude that the proposed method can successfully remove super-high-density noise with noise level above 90%.

     

量子衍生PDE医学超声图像去斑

目的 医学超声图像常常受到斑点噪声的污染而导致质量降低,影响后续诊疗.为了解决医学超声图像在滤波去斑的同时保持图像边缘细节和结构特征的问题,借鉴量子力学的基础理论,提出一种量子衍生偏微分方程(PDE)医学超声图像去斑方法.方法 针对传统P-M方程各向异性扩散的自适应去斑能力有限的问题,引入量子理论改进扩散系数增强去斑算法的自适应能力.同时构造出各向异性扩散模型,提出一种量子衍生的偏微分方程医学超声图像去斑方法.结果 通过对模拟斑点噪声污染的图像和真实医学超声图像实验,比较信噪比(SNR)、边缘保持度、结构相似度(SSIM)等客观评价指标,本文方法较其他图像去斑方法更能有效去除斑点噪声,同时又能较好地保持图像边缘细节与结构特征.结论 本文方法能够有效地解决医学超声图像去斑中保持图像细节特征的问题,同时,量子理论的引入也为后续医学超声图像的研究提供了新思路.     

基于最大后验概率和鲁棒估计的图像恢复推广变分模型

基于最大后验概率和MRF理论的图像恢复描述框架,提出一个面向图像恢复的推广变分模型.模型中将噪声建模为广义正态分布,利用最大似然法估计形状参数自动选择合适的范数作为数据保真项;将图像梯度场的分布建模为混合密度类,利用鲁棒估计理论构造一个耦合全变差积分和Dirichlet积分的图像先验模型作为正则化项.利用推广泛函的凸性,讨论了该推广模型的最优解存在性.最后提出结合梯度加权最速下降和半点格式的数值迭代算法.实验结果表明,推广模型能自动区分污染图像中的噪声分布特性,对于高斯噪声和脉冲噪声的污染图像都能取得很好的恢复效果.通过计算峰值信噪比和边缘保护指数,分析和评价了推广模型与目前其他变分方法的性能.     

Enhanced GPU-Based Anti-Noise Hybrid Edge Detection Method

Today, there is a growing demand for computer vision and image processing in different areas and applications such as military surveillance, and biological and medical imaging. Edge detection is a vital image processing technique used as a pre-processing step in many computer vision algorithms. However, the presence of noise makes the edge detection task more challenging; therefore, an image restoration technique is needed to tackle this obstacle by presenting an adaptive solution. As the complexity of processing is rising due to recent high-definition technologies, the expanse of data attained by the image is increasing dramatically. Thus, increased processing power is needed to speed up the completion of certain tasks. In this paper,we present a parallel implementation of hybrid algorithm-comprised edge detection and image restoration along with other processes using Computed Unified Device Architecture (CUDA) platform, exploiting a Single Instruction Multiple Thread (SIMT) execution model on a Graphical Processing Unit (GPU). The performance of the proposed method is tested and evaluated using well-known images from various applications. We evaluated the computation time in both parallel implementation on the GPU, and sequential execution in the Central Processing Unit (CPU) natively and using Hyper-Threading (HT) implementations. The gained speedup for the naïve approach of the proposed edge detection using GPU under global memory direct access is up to 37 times faster, while the speedup of the native CPU implementation when using shared memory approach is up to 25 times and 1.5 times over HT implementation.     

椒盐噪声下图像直方图的行为

重获噪声图像的原始直方图有助于确定像素的原始灰度值。本文讨论了脉冲噪声下图像直方图的行为,给出了由噪声图像直方图直接或近似估计原始图像直方图的公式,表明 了公式的收敛性,并作了仿真验证。结果成功地应用于高椒盐噪声图像的恢复问题。     

Motion-Blurred Image Restoration Based on Joint Invertibility of PSFs

To implement restoration in a single motion blurred image, the PSF (Point Spread Function) is difficult to estimate and the image deconvolution is ill-posed as a result that a good recovery effect cannot be obtained. Considering that several different PSFs can get joint invertibility to make restoration well-posed, we proposed a motion-blurred image restoration method based on joint invertibility of PSFs by means of computational photography. Firstly, we designed a set of observation device which composed by multiple cameras with the same parameters to shoot the moving target in the same field of view continuously to obtain the target images with the same background. The target images have the same brightness, but different exposure time and different motion blur length. It is easy to estimate the blur PSFs of the target images make use of the sequence frames obtained by one camera. According to the motion blur superposition feature of the target and its background, the complete blurred target images can be extracted from the observed images respectively. Finally, for the same target images with different PSFs, the iterative restoration is solved by joint solution of multiple images in spatial domain. The experiments showed that the moving target observation device designed by this method had lower requirements on hardware conditions, and the observed images are more convenient to use joint-PSF solution for image restoration, and the restoration results maintained details well and had lower signal noise ratio (SNR).     

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.     

Convolutional neural network-based restoration method of basketball contour image

Basketball image restoration is the process of taking damaged / noise images and predicting clean, original images. The vulnerability can take many forms such as motion blur, noise and camera misfocusing. Image Reconstruction Performed by this imaging point source, which is activated by converting blurred image, the so-called point diffusion function (including line) using the dot source image to recover the lost blurring process image information. The traditional outline tracking algorithm for basketball shooting dynamic hand image is vague, has poor stability and takes a long time. Recurrence nest tracking algorithm based on the dynamic boundary. The motion that the camera arm monitors are used to determine the target of the curve. The effective stiffness matrix is ​​obtained by initial calculation, as well as by using the characteristic curve recurrence calculation. The system image will then be applied to the dynamic boundary, where the energy is reduced to the target boundary. The purpose of basketball image restoration technology is to reduce noise and restore image processing technology's resolution loss in one of the image domain or frequency domains. Image restoration for basketball is performed on the frequency field except for the most direct previous art. It is computed by Fourier image and PSF, and the presence of convolution transforms the resolution loss caused by the blur factor. The probability sample is representing the entire population of sub-normal distribution with a Gaussian mixture model. The hybrid system, under normal conditions, which belongs to a subset of the data point seems obvious that this is a graded without learning is a subfield     

An Edge-Preserving Image Reconstruction Using Neural Network

This paper presents an image restoration model based on the implicit function theorem and edge-preserving regularization. We then apply the model on the subband-coded images using the artificial neural network. The edge information is extracted from the source image as a priori nowledge to recover the details and reduce the ringing artifact of the subband-coded image. The multilayer perceptron model is employed to implement the restoration process. The main merit of the presented approach is that the neural network model is massively parallel with strong robustness for the transmission noise and parameter or structure perturbation, and it can be realized by VLSI technologies for real-time applications. To evaluate the performance of the proposed approach, a comparative study with the set partitioning in hierarchical tree (SPIHT) has been made by using a set of gray-scale digital images. The experimental results showed that the proposed approach could result in compatible performances compared with SPIHT on both objective and subjective quality for lower compression ratio subband coded image.