Improved Weight Function for Nonlocal Means Image Denoising

The nonlocal means( NLM) has been widely used in image processing. In this paper,we introduce a modified weight function for NLM denoising, which will compute the nonlocal similarities among the pre-processing pixel patches instead of the commonly used similarity measure based on noisy observations. By the law of large number,the norm for the pre-processing pixel patches is closer to the norm of the original clean pixel patches,so the proposed weight functions are more optimized and the selected similar patches are more accurate. Experimental results indicate the proposed algorithm achieves better restored results compared to the classical NLM's method.

GAUSSIAN PRINCIPLE COMPONENTS FOR NONLOCAL MEANS IMAGE DENOISING

NonLocal Means(NLM),taking fully advantage of image redundancy,has been proved to be very effective in noise removal.However,high computational load limits its wide application.Based on Principle Component Analysis(PCA),Principle Neighborhood Dictionary(PND) was proposed to reduce the computational load of NLM.Nevertheless,as the principle components in PND method are computed directly from noisy image neighborhoods,they are prone to be inaccurate due to the presence of noise.In this paper,an improved scheme for image denoising is proposed.This scheme is based on PND and uses preprocessing via Gaussian filter to eliminate the influence of noise.PCA is then used to project those filtered image neighborhood vectors onto a lower-dimensional space.With the preproc-essing process,the principle components computed are more accurate resulting in an improved de-noising performance.A comparison with some NLM based and state-of-art denoising methods shows that the proposed method performs well in terms of Peak Signal to Noise Ratio(PSNR) as well as image visual fidelity.The experimental results demonstrate that our method outperforms existing methods both subjectively and objectively.

Local edge direction based non-local means for image denoising

Classic non-local means (CNLM) algorithm uses the inherent self-similarity in images for noise removal. The denoised pixel value is estimated through the weighted average of all the pixels in its non-local neighborhood. In the CNLM algorithm, the differences between the pixel value and the distance of the pixel to the center are both taken into consideration to calculate the weighting coefficients. However, the Gaussian kernel cannot reflect the information of edge and structure due to its isotropy, and it has poor performance in flat regions. In this paper, an improved non-local means algorithm based on local edge direction is presented for image denoising. In edge and structure regions, the steering kernel regression (SKR) coefficients are used to calculate the weights, and in flat regions the average kernel is used. Experiments show that the proposed algorithm can effectively protect edge and structure while removing noises better when compared with the CNLM algorithm.

Image Denoising Algorithm Considering Nonlocal Texture Pattern

Image denoising is indispensable for image processing.In this paper,image denoising algorithm based on Nonlocal Means(NLM)filter is proposed.Recently,abundant enhancements based on NLM filter have been performed.However,the performance of NLM filter is still inferior to that of other image processing approaches such as K-SVD.In this paper,NLM algorithm with weight refinement is utilized for image denoising.Weight refinement is performed to thoroughly take advantage of self-similarity of the image.Experimental results show good performance of the proposed method.

Local Orientation Field Based Nonlocal Means Method for Fingerprint Image De-Noising

The de-noising of the fingerprint image is one of the key tasks before the extraction of the minutiae in automatic fingerprint matching. When used for de-noising the fingerprint image, the nonlocal means method can not preserve the local minutiae in the fingerprint image very well. To address this problem, we propose a local orientation field based nonlocal means (NLM-LOF) method in this paper. Experimental results on the simulated and real images show that the proposed method can suppress noise effectively while preserving edges and details in the fingerprint image and it outperforms the state-of-art nonlocal means method in terms of qualitative metrics and visual comparisons.

基于改进NL-means算法的显微CT图像降噪

显微CT(Computed Tomography)采用微焦点射线源,射线剂量低,CT图像噪声大,对其降噪十分必要.综述了现存主要CT图像降噪算法及其优缺点,介绍了NL(nonlo-cal)-means算法,根据实验结果分析了其会在图像平滑区域引入人工伪影的不足.根据NL-means算法的不足,在原算法中引入图像的梯度信息,提出了改进的降噪算法,改进算法保持了原算法优良的降噪功能,并能有效抑制人工伪影,且能够提高图像细节对比度,实验结果验证了改进算法的有效性.

Nonlocal-Means Image Denoising Technique Using Robust M-Estimator

Edge preserved smoothing techniques have gained importance for the purpose of image processing applications A good edge preserving filter is given by nonlocal-means filter rather than any other linear model based approaches. This paper explores a different approach of nonlocal-means filter by using robust M-estimator function rather than the exponential function for its weight calculation. Here the filter output at each pixel is the weighted average of pixels with surrounding neighborhoods using the chosen robust M-estimator function. The main direction of this paper is to identify the best robust M-estimator function for nonlocal-means denoising algorithm. In order to speed up the computation, a new patch classification method is followed to eliminate the uncorrelated patches from the weighted averaging process. This patch classification approach compares favorably to existing techniques in respect of quality versus computational time. Validations using standard test images and brain atlas images have been analyzed and the results were compared with the other known methods. It is seen that there is reason to believe that the proposed refined technique has some notable points.

Filter Bank Based Nonlocal Means for Denoising Magnetic Resonance Images

Image denoising is a classical problem in image processing. Its essential goal is to preserve the image features and to reduce noise effiectively. The nonlocal means(NL-means) filter is a successful approach proposed in recent years due to its patch similarity comparison. However, the accuracy of similarities in this algorithm degrades when it suffiers from heavy noise. In this paper, we introduce feature similarities based on a multichannel filter into NL-means filter. The multi-bank based feature vectors of each pixel in the image are computed by convolving from various orientations and scales to Leung-Malik set(edge, bar and spot filters), and then the similarities based on this information are computed instead of pixel intensity. Experiments are carried out with Rician noise. The results demonstrate the superior performance of the proposed method. The wavelet-based method and traditional NL-means in term of both mean square error(MSE) and perceptual quality are compared with the proposed method, and structural similarity(SSIM) and quality index based on local variance(QILV) are given.

An Improved Image Denoising Algorithm Based on Structural Similarity and Curvelet

An image denoising method based on curvelet within the framework of non-local means(NLM) is proposed in this paper. We use Structural Similarity(SSIM) to compute the value of SSIM between the reference patch and its similar versions, and remove the dissimilar pixels. Besides, the curvelet is adopted to adjust the coefficients of these patches with low SSIM. Experiments show that the proposed method has the capacity to denoise effectively, improves the peak signal-to-noise ratio of the image, and keeps better visual result in edges information reservation as well.

基于融合距离的极化SAR图像非局部均值滤波

在极化合成孔径雷达(synthetic aperture radar,SAR)图像降噪领域,常见的非局部均值滤波仅依靠像素间的统计距离进行相似性度量,忽略了像素点的空间信息。本文结合极化SAR数据统计特性和图像空间特征作为像素间的相似性度量,提出了一种利用融合距离来计算相邻窗口权重的方法——基于融合距离的非局部均值滤波器。融合距离的引入使得滤波器能够更全面的评估像素间的相似性,从而得到更合适的像素权重。此外,本方法还引进变异系数对邻域窗口的权重进行评估,通过该参数可以控制滤波的程度。在多幅极化SAR图像上的实验结果表明,所提出的滤波器能够在有效抑制斑点噪声的同时保留较为完整的图像边缘信息和极化散射特性。

基于BM3D的脑MRI图像噪点剔除算法

磁共振成像(Magnetic Resonance Imaging,MRI)已经成为一种常见的影像检查方式,MRI的去噪算法影响着MRI的成像效果。基于深度学习的MRI去噪算法需要一定量的数据,绝大部分基于非深度学习的MRI去噪算法都是将MRI数据转化为实数之后进行去噪的,针对复数MRI中的复数数据类型的算法也存在着失真的问题。因此,提出一种通过单张MRI脑图像的原始数据进行噪点剔除的算法,以此更好得去除图像噪声。该算法从MRI的原始数据出发,利用了MRI噪声分布性质和MRI脑图像的特点,以判断MRI图像中噪声明显的点,从而剔除MRI中特定的莱斯分布的噪声。并将所提出的算法结合了MRI去噪中常用的非局部平均算法(Non-Local Means denoising,NLM)与三维块匹配算法(Block-Matching and 3D filtering,BM3D),并和不使用该算法剔除噪点的NLM、BM3D进行了对比评估。对比结果表明,在噪声密度不同的多种情况下,该算法总能优化与之相结合的图像去噪算法,在不同的噪声情况下使峰值信噪比(Peak Signal-to-Noise Ratio,PSNR)与结构相似性(Structural Similarity,SSIM)提高了1%~9%。最后将该算法结合BM3D,对比了DnCNN、低秩聚类算法(Weighted Nuclear Norm Minimization,WNNM)、BM3D、NLM等用于MRI去噪的算法,在莱斯噪声较多时,该算法在PSNR上有更好的表现。

基于改进NLM的PCB图像去噪算法

针对工业生产中的PCB图像边缘信息缺失且携带有大量噪声,现有去噪算法效果不佳、计算量庞大、复杂度高等问题,提出了一种基于改进NLM的PCB图像去噪算法,旨在提高PCB图像的去噪质量。首先,采用基于形态学的权重自适应算法对PCB图像进行图像增强,使PCB图像保留较好的边缘信息;其次,引入特征匹配模型对增强后的PCB图像与原始PCB图像进行特征点匹配融合;最后,通过改进NLM算法的权重值对PCB图像进行去噪,得到最终的去噪图像。实验结果显示,与现有算法相比,所提算法更好地保留了PCB图像的边缘信息,去噪效果佳,显著改善了图像质量,增强了图像的鲁棒性,且提高了计算速度,降低了算法复杂度。

Speckle noise reduction in digital holography with spatial light modulator and nonlocal means algorithm

An integrated method based on optical and digital image processing is presented to suppress speckle in digital holography. A spatial light modulator is adopted to introduce random phases to the illuminating beam. Multiple holograms are reconstructed and superimposed, and the intensity is averaged to smooth the noise. The adaptive algorithm based on the nonlocal means is designed to further suppress the speckle. The presented method is compared with other methods reduction is improved, and the proposed method is effective The experimental results show that speckle and feasible.

一种2D-VMD与NLM结合的芯片图像去噪算法研究

为了提高智能电表芯片图像的字符识别精度,需要消除芯片图像中的噪声,以减小干扰;文章提出了一种基于二维变分模态分解算法(2D-VMD)与非局部均值(NLM)滤波的芯片图像去噪算法;首先利用2D-VMD将含有噪声信号的芯片图像分解为K个模态分量;然后根据提出的结构相似(SSIM)阈值设置方法确定噪声分量并将其去除,使用剩余的有效分量重构图像;最后通过非局部均值滤波算法对重构后的图像进行处理,进一步滤除残余噪声,达到二次去噪的效果;实验结果表明,相比传统的图像去噪算法,提出的算法能在较好保留原始芯片图像的字符信息的基础上,去除不相关的噪声干扰,使去噪后的芯片图像的均方误差值变小,峰值信噪比增大,提高芯片图像质量。

基于NLM算法的加权核函数选取研究

非局部均值去噪算法利用图像邻域间具有自相似性这一特性,通过加权核函数得到图像中相似图像块的权重,进而达到图像去噪目的。将基于MATLAB平台与传统NLM算法,设计实验令多种加权核函数分别对加高斯白噪声的图像进行去噪处理,再利用图像主观质量评价方法与客观评价方法进行结果分析,一方面可以证明选择合适的加权核函数对于改善去噪效果的必要性,另一方面得到在不同强度高斯白噪声时图像应选择的最佳加权核函数。

基于非局部结构张量的图像去噪算法

针对非局部均值滤波在计量像素补丁之间的相似度不够准确的问题,该文先引入各向同性中心凹算子对像素补丁进行预处理,以抑制噪声的不良影响,随后再进行相似度计算,且为了充分利用图像中像素点的几何结构等细节信息,进一步提出了基于非局部结构张量的非局部均值去噪算法。实验结果表明,所提算法相较于传统非局部均值去噪(NLM)和基于结构张量的非局部均值去噪(STNL)在峰值信噪比上分别提高了6.57%、2.1%,同时视觉呈现上也有明显提升。

采用非局部均值的超分辨率重构

由于传统的超分辨率重构无法在工程应用中对含有局部运动图像进行有效的运动估计及重构,本文提出一种采用非局部均值(NLM)的超分辨率重构方案。简要介绍了具有较好去噪特性的非局部均值滤波器,分析了超分辨率重构的代价函数,根据构造出的非局部均值超分辨率重构算法的代价函数及其求解,对提出的方案进行进一步的优化和化简,最后得到一种易于工程实现的重构算法。实验结果表明,提出的算法不仅具有NLM算法的优点,即不需进行显式的运动估计就能得到更清晰、细节更丰富的重构图像;而且重构速度比简化前的NLM算法提高将近30%,有望应用于具有复杂运动的图像的超分辨率重构。

DCT子空间的非局部均值去噪算法

在整个图像块像素灰度值向量空间中,非局部均值(nonlocal means,NLM)算法度量像素间的相似性不仅计算复杂度高,而且当噪声存在时还不能准确地计算出像素间的相似性权重值,影响了对图像冗余性质的利用,使得去噪结果图像对比度和清晰度低.针对NLM算法的这一缺陷,利用离散余弦变换(discrete cosine transform,DCT)的低数据相关性和高能量紧致性,将DCT与NLM算法相结合,对图像块进行DCT,并在DCT低频系数子空间内度量像素间的相似性.实验结果表明,与NLM算法相比,该方法能够在保护图像结构信息、对比度和清晰度的前提下更有效地去除噪声,峰值信噪比值一般可以提高1dB以上,运行时间不到NLM算法的1/10.

选择性计算的快速非局部均值图像去噪

针对非局部均值(NLM)图像去噪算法度量像素间的相似性计算强度高的问题,提出了一种选择性计算的快速NLM去噪方法。在图像块像素灰度值向量空间距离计算时,利用L2范数逐次消元法,只需在图像积分图上通过少量加法运算即可剔除大量相似性低的像素点,有效地减少计算强度。根据图像空间相关性强的特点,提出了基于patch测地线距离的动态调整搜索区域的方法。实验结果表明,与其他经典算法相比,该方法获得了较好的加速,也提升了NLM算法的去噪性能。

基于非局部平均滤波的冲击噪声图像恢复算法

针对随机值冲击噪声污染图像的恢复问题,研究了冲击噪声环境下的非局部平均滤波模型,并在模糊权重非局部平均滤波算法的基础上加以改进,解决了原算法在低噪声比率下恢复性能欠佳以及算法时耗过高的问题。提出了一种信赖度参数设置准则,并在该准则指导下设置了新的信赖度门限参数;根据冲击噪声模型特点重新规划了滤波策略,提升了算法的运算效率。大量实验数据证明,所提算法无论在低噪声比率还是高噪声比率下均能有效去除冲击噪声,尤其对于纹理性较强的图像有显著的去噪效果;同时,所提算法拥有较高运算效率,实用性得以提高。