一种应用于图像去噪的广义回归神经网络模型设计研究

为了更好地去除图像中的椒盐噪声、保留图像细节信息,提出了一种广义回归神经网络模型,适用于图像去噪。首先,对传统广义回归神经网络的原理进行了分析,并对采用的广义回归神经网络进行具体设计。然后对广义回归神经网络中的唯一可调参数（平滑因子）进行了优化。采用归一化均方误差和峰值信噪比指标进行具体算法性能分析。仿真试验结果显示：相比径向基神经网络和传统广义回归神经网络,提出算法的去噪能力更强,具有较高的峰值信噪比和较低的归一化均方误差,验证了提出算法的有效性和先进性。     

Magnetic resonance image denoising using nonlocal maximum likelihood paradigm in DCT‐framework

The data acquired by magnetic resonance (MR) imaging system are inherently degraded by noise that has its origin in the thermal Brownian motion of electrons. Denoising can enhance the quality (by improving the SNR) of the acquired MR image, which is important for both visual analysis and other post processing operations. Recent works on maximum likelihood (ML) based denoising shows that ML methods are very effective in denoising MR images and has an edge over the other state‐of‐the‐art methods for MRI denoising. Among the ML based approaches, the Nonlocal maximum likelihood (NLML) method is commonly used. In the conventional NLML method, the samples for the ML estimation of the unknown true pixel are chosen in a nonlocal fashion based on the intensity similarity of the pixel neighborhoods. Euclidean distance is generally used to measure this similarity. It has been recently shown that computing similarity measure is more robust in discrete cosine transform (DCT) subspace, compared with Euclidean image subspace. Motivated by this observation, we integrated DCT into NLML to produce an improved MRI filtration process. Other than improving the SNR, the time complexity of the conventional NLML can also be significantly reduced through the proposed approach. On synthetic MR brain image, an average improvement of 5% in PSNR and 86%reduction in execution time is achieved with a search window size of 91 × 91 after incorporating the improvements in the existing NLML method. On an experimental kiwi fruit image an improvement of 10% in PSNR is achieved. We did experiments on both simulated and real data sets to validate and to demonstrate the effectiveness of the proposed method. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 256–264, 2015     

Reduction of speckle noise from optical coherence tomography images using multi-frame weighted nuclear norm minimization method

In this paper, we propose a speckle noise reduction method for spectral-domain optical coherence tomography (SD-OCT) images called multi-frame weighted nuclear norm minimization (MWNNM). This method is a direct extension of weighted nuclear norm minimization (WNNM) in the multi-frame framework since an adequately denoised image could not be achieved with single-frame denoising methods. The MWNNM method exploits multiple B-scans collected from a small area of a SD-OCT volumetric image, and then denoises and averages them together to obtain a high signal-to-noise ratio B-scan. The results show that the image quality metrics obtained by denoising and averaging only five nearby B-scans with MWNNM method is considerably better than those of the average image obtained by registering and averaging 40 azimuthally repeated B-scans.     

基于最优复Morlet小波的结构密集模态参数识别

针对结构密集模态参数识别精度不高的问题,提出了一种小波Shannon熵与最小标准差相结合来优化复Morlet小波参数的方法。首先理论推导了中心频率与带宽参数的取值范围,其次采用两个最小原则对中心频率与带宽参数同时进行优化,通过仿真算例和模型实验的参数识别,验证了参数优化后的Morlet小波可准确地识别结构的密集模态参数,并且具有一定的抗噪性能。     

露天转地下开采边坡爆破振动小波能量分析

为了分析露天转地下开采高陡边坡爆破振动特征,实现矿山安全高效开釆,根据爆破振动信号的非平稳、复合特点,结合大冶矿山露天转地下开采高陡边坡爆破振动实测数据,利用小波变换的多分辨率特征对爆破振动信号进行小波变换和小波频带能量特征分析。分析结果表明:db8小波函数变换能有效精确地分析爆破振动信号;爆破振动能量的优势频段为31.25~62.5 Hz,远大于岩质边坡的固有频率,爆破振动对边坡岩体结构影响有限;边坡爆破振动能量在不同方向上的大小不同,在指向边坡自由面的水平方向上的爆破振动能量最大,应重点分析。     

车用发动机凸轮轴轴承松脱的故障特征提取

车用发动机凸轮轴轴承松脱故障使得凸轮轴受力不均而引起冲击力,导致凸轮轴附近机体表面出现异常振动和显著噪声。通过对某发动机凸轮轴轴承松脱故障的试验测试,提取缸盖振动加速度信号进行时域分析,发现有明显的周期性冲击;利用小波包分解至较高频段并做解调分析,解调谱的故障激励频率非常显著。分析结果表明,凸轮轴轴承松脱故障有中高频调制现象,可综合利用时域分析、频谱分析和小波包分解与解调分析进行相应的故障特征提取。     

基于小波包分析和Kohonen神经网络相结合的轴承故障诊断

简述了小波包分析及用于特征提取的机理,以SKF 6326-C3轴承为例,从吉林同发风电场采集了不同工况下的实时信号,利用小波包对滚动轴承振动信号进行分解,振动信号被分解到独立的频段。不同频带内的信号能量变化反映了运行状态的改变,提取各频带小波包能量谱,并对其进行能量归一化处理,作为特征向量,最后应用于基于Kohonen神经网络的故障诊断方法。经对大量实测数据的处理和分析,能够比较准确地诊断出轴承的故障。     

低信噪比通信信号的自适应调参随机共振方法

参数调节随机共振系统中参数的选择对输出信号的效果优劣具有决定性作用.本文针对目前随机共振无法通用地处理多类微弱通信信号的问题，提出基于自适应调参随机共振的信号增强方法.首先，从信号的特征子空间角度阐释了随机共振的能量转移本质，提出将基于奇异值分解的测度函数作为评价函数进行寻优.其次，在分析了两个不同系统参数的作用后，利用幅度归一化对单参数优化，降低了复杂度，并将滑动平均滤波器加入随机共振模块来防止幅度漂移.最后，以人工鱼群算法为基础，模块化设计出方法的整体框架和具体步骤.仿真结果表明，针对四类共九种信号，该方法能够以平均4至5次的迭代收敛速度实现带噪声的信号和非线性系统的匹配.     

基于LP与小波包的复杂机电系统监测序列混沌降噪方法

针对流程工业生产系统监测数据存在强噪声和混沌性的特点,提出了一种局部投影方法(Local Projection Method)与小波包方法相结合的信号降噪方法。该方法先利用局部投影方法从动力学系统嵌入流形的角度进行多次迭代降噪,并根据关联维数来判定迭代终止;再利用小波包方法从频率的角度进行降噪,抑制高频噪声的干扰,取得了较好的降噪效果。用Lorenz时间序列进行仿真验证,对仿真时间序列加入不同程度的噪声,对比分析小波包、局部投影与该方法降噪后的相空间、SNR值和最大Lyapunov指数,证明了该方法对于中高强度噪声具有更好的降噪效果。并将该方法用于某压缩机组的实际监测数据降噪,评估三种方法的降噪效果,进一步验证了该方法的优越性。     

一种基于全变分技术和Lp伪范数的椒盐噪声去除方法

针对传统各向同性全变分（Isotropy total variation，ITV）去噪算法容易导致图像边缘模糊、不易保持图像细节信息等问题，提出一种基于L _p 伪范数和各向同性全变分的图像去噪方法。该方法将L _p 伪范数代替ITV模型中的L ₁范数，利用交替方向乘子算法（Alternating direction method of multipliers, ADMM）将能量泛函拆解成若干个子问题，并将差分算子视为卷积算子；然后引入卷积定理和快速傅里叶变换(Fast Fourier transform, FFT)提高算法运算效率；最后通过Matlab进行仿真实验，运用图像质量的客观和主观评价方法进行评价分析。结果表明，本文方法能够较好地保留图像的边缘特性，有效提升去噪效果。