基于神经网络的图像混合滤波及融合算法研究

当图像中同时存在高斯噪声和椒盐噪声时,单一的均值滤波或中值滤波很难达到最佳滤波效果。 分析了噪声特点和各种滤波方法的优势,提出了一种基于神经网络的图像混合滤波及融合算法:首先建立概率神经网络,检测椒盐噪声和高斯噪声点,并分别利用中值滤波和均值滤波去除噪声点,然后建立径向基函数神经网络,利用训练好的径向基函数神经网络融合 2 种不同滤波的图像,输出理想的融合图像。 Matlab 仿真实验结果表明,该算法有效去除混合噪声的同时,能很好地保护图像的边缘与细节,是一种有效的方法。     

去除脉冲噪声的自适应开关中值滤波

为消除图像中的脉冲噪声,提出了自适应开关中值(ASM)滤波算法。该算法采用一种新的噪声检测方法将图像中的像素分为信号点和噪声点两类。对检测出的噪声点统计其个数并由此估算图像中的噪声密度,根据估计的噪声密度自适应确定滤波窗口尺寸,采用改进的中值滤波对检测出的噪声点进行处理;而信号点则保留其灰度值不予处理。对ASM滤波进行仿真实验,结果表明,它能在有效去除噪声的同时很好地保护图像细节,较传统中值滤波及其它改进中值滤波算法有更优的滤波性能。     

基于提升格形态小波的生物芯片图像增强

提出一种使用提升格形态小波进行生物芯片图像滤波增强的方法。根据生物芯片图像的样点和噪声区域的大小选择合适的结构元素或者预测-升级算子，并通过形态学算子或者提升格构造形态小波分解和重构形式。利用形态小波的不同级连方式和高频系数的处理实现生物芯片图像的滤波增强。实验表明，该方法可以有效地结合形态学和小波滤波的优势，降低了运算量，取得良好的生物芯片图像增强效果。     

基于数学形态学的图像去噪方法研究

在噪声污染图像的处理中,运用数学形态学的理论和方法,提出了一种多结构元素自适应确定权重的算法,在此基础上构造开、闭运算的串、并复合形态滤波器。在形态滤波过程中,采用由小到大的多结构元进行处理以达到几乎全部滤除噪声的目的。实验表明,这类滤波器不仅可以有效地抑制图像中的噪声,而且较好地保持了图像的几何特征。     

基于形态学的海面背景红外点目标检测方法

采用行均值相减方法抑制温度场的非线性影响,校正红外图像模糊,增强点目标;利用Top-Hat算子形态滤波,抑制背景并保留高亮区;选择结构元素进行腐蚀和膨胀运算,去除虚警点获得目标候选点;搜索局部极大值,确定阈值并结合图像帧间的相关性分离出目标。实验表明,该方法能检测出低信噪比复杂海面背景中的红外点目标。     

新颖的CB形态学串并复合散斑噪声滤波器

基于轮廓结构元素形态学(CB形态学)和广义多结构元素的数学形态学,构造了一种新颖的用于抑制图像中的散斑噪声的串并复合滤波器.首先采用全方位多结构元素的广义多刻度形态开最大滤波器与广义多刻度形态闭最小滤波器相并联的滤波器进行滤波,力求在滤波的同时图像几何细节损失尽可能少,然后通过级联的CB开和CB闭滤波器,再滤除剩余的斑点噪声,从而在有效抑制图像中的散斑噪声的同时更好地保持了图像的细节信息.分析和仿真表明了本文提出的滤波算法的有效性.     

基于阈值判断的自适应中值滤波算法

针对标准的中值滤波算法在去除噪声与保留图像细节方面难以取舍的缺陷,在自适应中值滤波算法的基础上提出了一种改进的基于噪声点检测的自适应中值滤波算法.该算法在进行噪声点检测时采用了一种阈值判断法,充分利用了当前像素点与邻域像素点的灰度值之间的关系.结果表明,在噪声浓度较高时仍然可以区分噪声点与边缘点,滤波的同时有效地保护了图像的细节.     

基于噪声点多级检测的自适应中值滤波算法

针对传统中值滤波算法在图像去噪过程中造成较多图像细节信息丢失的问题,提出了一种基于噪声点多级检测的自适应中值滤波算法。该算法根据像素的空间相关性,逐级检测不同空间特征的噪声点。首先根据滤波窗口中相近像素点的数量来检测空间孤立的单个噪声点;然后通过扩展邻近窗口的方式检测空间连续的两个噪声点;接着进一步增加约束条件对空间连续的三个及以上的噪声点进行检测;最后对判断为噪声的像素用滤波窗口的中值替换。此外,该算法还能通过自适应地调整像素空间相关性判别阈值来处理不同分布特征的噪声。实验结果表明,与现有中值滤波算法相比,算法在有效滤除图像噪声的同时能更好地保护图像细节信息。     

基于图像去噪的混合噪声滤波算法

传统的中值滤波和均值滤波通常被分别用来滤除椒盐噪声和高斯噪声.但是当图像同时存在高斯噪声和椒盐噪声时,单独使用哪种滤波方法都不会达到最好的去噪效果.为了能同时滤除两种不同性质的噪声,提出了一种新的自适应混合噪声滤波算法.该算法采用了一种基于自适应阈值的方法对滤波系数加以优化,使其既可以有效地减少噪声,又可以较好的保持图像的边缘细节信息,仿真结果表明该算法能较好的滤除混合噪声,且滤波效果优于传统的滤波算法.     

一种特征点跟踪的运动目标检测

提出一种基于特征点跟踪的运动目标分割算法。在角点跟踪过程中,8等分匹配点邻域,构造方向子邻域提高匹配精度;提出一种新的聚类准则抽取最优特征子集估计运动参数;结合统计方法消除残差噪声;采用时域滤波滤除孤立区域检测出运动目标。对200帧可见光视频序列和100帧红外图像序列中运动汽车进行检测分割实验,检出率分别达到96%和94%。     

Adaptive-neighborhood speckle removal in multitemporal synthetic aperture radar images

We present a new method for multitemporal synthetic aperture radar image filtering using three-dimensional (3D) adaptive neighborhoods. The method takes both spatial and temporal information into account to derive the speckle-free value of a pixel. For each pixel individually, a 3D adaptive neighborhood is determined that contains only pixels belonging to the same distribution as the current pixel. Then statistics computed inside the established neighborhood are used to derive the filter output. It is shown that the method provides good results by drastically reducing speckle over homogeneous areas while retaining edges and thin structures. The performances of the proposed method are compared in terms of subjective and objective measures with those given by several classical speckle-filtering methods.     

Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery

It is well-known that speckle is a multiplicative noise that degrades the visual evaluation in ultrasound imaging. The recent advancements in ultrasound instrumentation and portable ultrasound devices necessitate the need of more robust despeckling techniques for enhanced ultrasound medical imaging for both routine clinical practice and teleconsultation. The objective of this work was to carry out a comparative evaluation of despeckle filtering based on texture analysis, image quality evaluation metrics, and visual evaluation by medical experts in the assessment of 440 (220 asymptomatic and 220 symptomatic) ultrasound images of the carotid artery bifurcation. In this paper a total of 10 despeckle filters were evaluated based on local statistics, median filtering, pixel homogeneity, geometric filtering, homomorphic filtering, anisotropic diffusion, nonlinear coherence diffusion, and wavelet filtering. The results of this study suggest that the first order statistics filter lsmv, gave the best performance, followed by the geometric filter gf4d, and the homogeneous mask area filter lsminsc. These filters improved the class separation between the asymptomatic and the symptomatic classes based on the statistics of the extracted texture features, gave only a marginal improvement in the classification success rate, and improved the visual assessment carried out by the two experts. More specifically, filters lsmv or gf4d can be used for despeckling asymptomatic images in which the expert is interested mainly in the plaque composition and texture analysis; and filters lsmv, gf4d, or lsminsc can be used for the despeckling of symptomatic images in which the expert is interested in identifying the degree of stenosis and the plaque borders. The proper selection of a despeckle filter is very important in the enhancement of ultrasonic imaging of the carotid artery. Further work is needed to evaluate at a larger scale and in clinical practice the performance of the proposed despeckle filters in the automated segmentation, texture analysis, and classification of carotid ultrasound imaging.     

A novel scheme for image sharpness using inflection points

It is useful to increase the sharpness in medical images. This improvement can help medical diagnoses and treatment outcomes for patients. Noise overshoot and oversharpening effects are common artifacts of conventional sharpening algorithms. In this work, we propose an adaptive sharpness algorithm that achieves better sharpening effects than standard methods. As the pixel value changes abruptly at an edge, a method that adequately emphasized sudden variations in pixel values is effective for use in the sharpening process. Measurement of the gradient norm value of each pixel is calculated and compared to a threshold value to produce a curve. The curve quickly drops at the initial stage and then decreased more slowly for higher norm values. To distinguish the edge, an inflection point is determined by taking the second derivative of the curve and identifying the turnover point (where the curvature changes sign). Norm values higher than the inflection point are identified as belonging to the edge, and a simple sharpness filter is adaptively applied to these points. The proposed approach yielded better results than global filtering and a conventional unsharp masking approach when evaluated using Pratt's figure of merit.     

General adaptive-neighborhood technique for improving synthetic aperture radar interferometric coherence estimation

A new method for filtering the coherence map issued from synthetic aperture radar (SAR) interferometric data is presented. For each pixel of the interferogram, an adaptive neighborhood is determined by a region-growing technique driven by the information provided by the amplitude images. Then pixels in the derived adaptive neighborhood are complex averaged to yield the filtered value of the coherence, after a phase-compensation step is performed. An extension of the algorithm is proposed for polarimetric interferometric SAR images. The proposed method has been applied to both European Remote Sensing (ERS) satellite SAR images and airborne high-resolution polarimetric interferometric SAR images. Both subjective and objective performance analysis, including coherence edge detection, shows that the proposed method provides better results than the standard phase-compensated fixed multilook filter and the Lee adaptive coherence filter.     

Speckle reduction in optical coherence tomography by adaptive total variation method

An adaptive total variation method based on the combination of speckle statistics and total variation restoration is proposed and developed for reducing speckle noise in optical coherence tomography (OCT) images. The statistical distribution of the speckle noise in OCT image is investigated and measured. With the measured parameters such as the mean value and variance of the speckle noise, the OCT image is restored by the adaptive total variation restoration method. The adaptive total variation restoration algorithm was applied to the OCT images of a volunteer’s hand skin, which showed effective speckle noise reduction and image quality improvement. For image quality comparison, the commonly used median filtering method was also applied to the same images to reduce the speckle noise. The measured results demonstrate the superior performance of the adaptive total variation restoration method in terms of image signal-to-noise ratio, equivalent number of looks, contrast-to-noise ratio, and mean square error.     

Ultrasound speckle reduction using modified Gabor filters

B-mode ultrasound images are characterized by speckle artifact, which may make the interpretation of images difficult. One widely used method for ultrasound speckle reduction is the split spectrum processing (SSP), but the use of one-dimensional (1-D), narrow-band filters makes the resultant image experience a significant resolution loss. In order to overcome this critical drawback, we propose a novel method for speckle reduction in ultrasound medical imaging, which uses a bank of wideband 2-D directive filters, based on modified Gabor functions. Each filter is applied to the 2-D radio-frequency (RF) data, resulting in a B-mode image filtered in a given direction. The compounding of the filters outputs give rise to a final image in which speckle is reduced and the structure is enhanced. We have denoted this method as directive filtering (DF). Because the proposed filters have effectively the same bandwidth as the original image, it is possible to avoid the resolution loss caused by the use of narrow-band filters, as with SSP. The tests were carried out with both simulated and real clinical data. Using the signal-to-noise ratio (SNR) to quantify the amount of speckle of the ultrasound images, we have achieved an average SNR enhancement of 2.26 times with simulated data and 1.18 times with real clinical data.     

Tissue stiffness imaging method using temporal variation of ultrasound speckle pattern

Applying vibration to a medium makes it vibrate. The resulting change in scatterer distribution inside the medium due to applied vibration changes the speckle pattern of ultrasound images. In this case, scatterers in a hard medium experience small displacements, and those in a soft medium experience large displacements. As a result, the amount of speckle pattern brightness change in ultrasound images is related to the tissue stiffness. Using this dependency, a two-dimensional profile of relative tissue stiffness can be constructed qualitatively at the display pixel resolution by determining at each pixel the standard deviation and/or the difference between minimum and maximum values over a certain number of consecutive B-mode images. Experiments with phantoms show that the softer the tissue, the larger the standard deviation. The proposed imaging modality is a simple yet practical method of resolving hard cysts surrounded by soft background in a phantom using B-mode frame data only.     

Ultrasound Speckle Reduction Based on Histogram Curve Matching and Region Growing

The quality of ultrasound scanning images is usually damaged by speckle noise. This paper proposes a method based on local statistics extracted from a histogram to reduce ultrasound speckle through a region growing algorithm. Unlike single statistical moment-based speckle reduction algorithms, this method adaptively smooths the speckle regions while preserving the margin and tissue structure to achieve high detectability. The criterion of a speckle region is defined by the similarity value obtained by matching the histogram of the current processing window and the reference window derived from the speckle region in advance. Then, according to the similarity value and tissue characteristics, the entire image is divided into several levels of speckle-content regions, and adaptive smoothing is performed based on these classification characteristics and the corresponding window size determined by the proposed region growing technique. Tests conducted from phantoms and in vivo images have shown very promising results after a quantitative and qualitative comparison with existing work.