基于曲率滤波和梯度变换的图像增强

针对基于梯度变换的图像增强算法抗噪声干扰能力差的问题,引入曲率滤波理论,提出了基于高斯曲率滤波和梯度变换的图像增强算法.该算法通过对图像梯度场进行非线性变换来增强图像对比度,通过构造能量泛函,采用梯度下降法从变换后的梯度场重构出增强后的图像,并利用高斯曲率滤波对梯度下降法迭代过程中的重构图像及其各阶偏微分进行平滑,有效解决了图像重构过程中的噪声非线性放大和扩散问题,同时保留了丰富的细节信息.采用多组边缘模糊图像进行仿真实验,实验结果表明该算法在增强图像边缘对比度的同时,能够有效抑制噪声.     

基于局部自适应拉升窗的复合图像增强算法

针对含有低亮度低对比度区域的图像,提出基于局部自适应拉升窗(LASW)的复合图像增强算法.通过研究目前一系列基于局部操作的空域图像增强算法,提出全局和局部操作结合的总体思路;首先使用高提升拉普拉斯(Laplacian)反锐化掩模(UM)增强以获得较多的隐藏细节和边缘信息,然后构造局部自适应拉升窗大幅增强低对比度图像细节,同时使用自适应滤波器进行掩模平滑操作;最后根据局部增强结果进行全局修正.仿真实验表明,在绝对误差、图像熵等评价指标下,该算法使低对比度图像尤其当含有低亮度微弱局部信息时,获得了较好的增强效果.     

MPPC low-level-light imaging enhancement algorithm based on sub-window box filtering北大核心CSCD

针对多像素光子计数器(MPPC)进行微光成像时,图像受光照不足和噪声影响出现的图像亮度低、对比度差、边缘模糊等问题,提出一种基于子窗口盒式滤波的自适应微光图像处理算法。为了减少算法运行时间的同时突出图像的边缘细节信息,利用子窗口盒式滤波器对图像进行分层得到基础层和细节层;对基础层图像采用自适应阈值直方图均衡化拉伸对比度,细节层图像采用自适应增益控制方式进行增强;根据基础层图像中有效灰度值个数占总灰度的比值自适应确定融合系数,将基础层图像与细节层图像融合得到增强后图像。通过微光实验平台设置3组不同照度的微光环境进行实验仿真,验证了本文算法在保持边缘信息和增强细节方面获得了更好的效果。实验结果表明本文算法在标准差、信息熵、平均梯度等客观评价方面优于改进前算法,提升了微光图像的成像效果。     

基于模糊集的自适应红外图像边缘锐化算法

针对红外图像边缘模糊和非均匀性噪音强的特点,提出了一种基于模糊集的自适应红外图像边缘锐化方法.针对图像边缘细节和噪音难以表示和区分的特点,分别建立噪音、弱边缘和强边缘的模糊特征隶属度函数,并且提取图像信息自适应调整隶属度函数;通过隶属度函数将图像映射到模糊特征平面,由模糊特征平面控制图像边缘锐化系数.该方法不仅能够锐化红外图像边缘,而且改善了传统边缘锐化算法对图像噪音放大的缺点,避免了对强边缘的过渡增强导致图像出现过增强现象,改善了图像质量.     

基于非线性反锐化掩模算法的CR图像边缘增强

数字CR(computed radiography)医学放射图像动态范围宽、细节丰富、对比度差,只有对其进行增强处理才能满足医生临床诊断的需要。由于目前通用的CR图像增强算法的对比度和噪声增强过度,丢失了细节,为了对CR图像进行边缘细节增强,提出了一种非线性反锐化掩模算法。该算法使用钝化模糊影像来增加对选择空间频率的响应,以增强CR图像的结构边缘和细节。算法能根据CR图像的灰度特性来调节增强程度的加权因数K,从而可非线性地增强CR影像的边缘细节。实验证明,经算法处理后的CR图像细节丰富,信噪比高,细节方差与背景方差之比为通用算法的9.6倍,增强后的CR图像具有良好的视觉效果,是一种增强CR医学放射图像边缘细节的好方法。     

基于引导滤波的自适应红外图像增强改进算法

在红外图像处理中,细节增强和噪声抑制尤为重要,重点在于将高动态范围的红外图像压缩至低动态范围的同时保留细节信息、抑制图像噪声。以引导滤波的自适应红外图像增强算法为基础,提出一种基于引导滤波的自适应红外图像增强改进算法。通过引导滤波平滑初始输入图像,将初始输入图像与平滑后的图像做差获得包含大动态温度信息的基础层图像和小动态温度信息的细节层图像,分别对基础层图像、细节层图像进行压缩处理和噪声抑制;以不同的融合比例将处理后的基础层图像、细节层图像进行融合获得输出图像。为了减少算法运算时间、突出图像细节信息的同时减小细节层噪声对输出图像的影响且达到自适应场景的效果,利用可用于筛选有效灰度值的自适应门限参数和直方图分布信息设计出一维压缩数组对图像进行压缩,并将图像融合中的定值比例系数更改为自适应融合比例系数。通过直方图分布信息中的最大值、最小值确定自适应门限参数,同时利用直方图分布信息设计出一维压缩数组对图像进行压缩;获取直方图中有效灰度值个数,通过有效灰度值个数与总灰度值个数之间的比值对图像的场景信息进行判断,根据不同的场景信息确定基础层图像与细节层图像的自适应融合比例系数,实现图像融合。实验结果分别与直方图均衡算法、基于引导滤波的高动态红外图像增强算法、基于引导滤波的自适应红外图像增强算法进行比较,选用四种不同的场景从主观、客观两种层面进行分析。对比结果从主观分析得出该算法处理后的图像可突出细节轮廓信息、减少细节层噪声对融合后输出图像的影响。从客观评价得出该算法在四种场景下的平均计算时间为0.753 5 s,低于对比算法计算时间;并且使基础层图像和细节层图像的融合比例系数达到自适应场景的效果。     

对一种新的基于局部标准差的自适应对比度增强算法的评价

介绍一种基于图像局部标准差变换的自适应增强算法通过将图像的局部标准差映射为高斯函数得到一个非线性对比度增益函数,使图像的细节区域得到较大幅度的增强,同时抑制平滑区域的噪声以及发生于陡峭边缘的“振铃伪迹”(Ringing Artifact)通过不同类型的图像以及对比度-噪声比(Contrast-to-Noise Ratio)演示了算法的性能,并与几种常用的图像增强方法进行了比较结果表明该算法对于低对比度的图像细节具有较好的增强效果,同时能够避免平滑区域噪声的过度增强及陡峭边缘的振铃伪迹.     

基于像素灰阶熵的自适应增强算法在乳腺CR图像中的应用

乳腺完全是由密度接近软组织构成,因此乳腺CR(Computed Radiography)放射图像对比度小,轻微的差别变化都可能是肿瘤的表现,要对其进行增强处理方能满足医生临床诊断的需要。而目前通用的乳腺CR图像增强算法对比度和噪声增强过度,丢失细节,为此提出了采用一种基于像素灰阶熵的自适应边缘增强算法对乳腺CR图像进行增强。该算法使用模糊影像增加对选择空间频率的响应,以增强乳腺CR图像结构边缘和细节;算法能根据乳腺CR图像灰度特性即像素灰阶熵来自适应的调节增强程度的加权因数K。实验证明,该算法处理后的乳腺CR图像细节丰富,信噪比高,增强后的图像具有良好的视觉效果,该算法是一种有效的适合乳腺CR医学图像的边缘细节增强算法。     

基于粗糙集与小波反锐化掩模的图像增强

为了有效去除图像中的干扰噪音,改善模糊不清晰的有用边缘细节信息,提高图像的层次感和清晰度,提出将粗糙集和小波反锐化掩模相结合的方法来实现图像增强.运用粗糙集中的近似及等价属性关系将知识化后的图像划分成不同的区域,再根据估计好的阈值进行数据约简,实现有效去除噪音.运用小波反锐化掩模法对图像的轮廓及细节信息进行增强处理,完成图像的最终增强.实验结果表明,不论在主观的视觉效果上,还是客观的噪音均方误差,该方法的处理结果都是较为理想的.     

基于Contourlet变换和形态学的图像增强方法

传统的图像增强算法在增强图像时,增大噪音,同时丢失细节.针对该问题,结合Contourlet变换中相关系数理论,提出了基于Contourlet变换和数学形态学的图像增强新算法.首先,对图像进行Contourlet变换分解,采用数学形态学算子对高频细节部分区分为细节信息和噪音产生的系数,然后,对变换系数采用非线性映射函数进行增强.最后,利用修改后的变换系数进行Contourlet逆变换得到增强后的图像.实验表明,该方法无论是增强效果还是抗噪性能都明显优于传统的图像增强算法.     

Novel infrared image enhancement technology based on the frequency compensation approach

A novel infrared image enhancement method has been proposed in this paper. Our aim is to develop a detail enhancement method which is focused on the frequency feature of the image. The proposed method is following the most popular strategy of enhancing the infrared images nowadays, but concentrating on the frequency domain. Firstly, the original image is separated by a guided image filter into detail layer and the base layer. Quite unlike the traditional methods, we use the guided image filter to eliminate most of the noise and weak signal of the scenario. Then, by a designed iteration process, the higher frequency of the scenario will be calculated back and add to the detail layer. The noise will not be enhanced because the iteration is only focused on the leftover scenario frequency. We run many tests on the raw data captured by the 320 × 256 HgCdTe cooled thermal imager, and make a comparison between our approach with the previous method of bilateral filtering digital detail enhancement and guided image filtering digital detail enhancement. Figures and analytical data show that our method is better than the previous proposed researches. Our method could effectively process the infrared image with less noise and artifacts, which has potential applications in testing, manufacturing, chemical imaging, night vision, and surveillance security.     

Sharpening enhancement of ultrasound images using contourlet transform

The furry regions of ultrasound images are to be enhanced for good quality visual perception. This paper proposes a contourlet transform (CT) based sharpening technique (ST) for contrast enhancement in ultrasound (US) images. While sharpening, noise emphasize is the drawback of the classical ST methods. The proposed ST is operated on the multiscale, multidirectional CT decomposition of the underlying US image. The new ST not only sharpens the US image but also control the noise effect with tunable parameters. The results are compared with common unsharp masking and recently proposed nonlinear unsharp masking. The parameters like enhancement measure, structural similarity, and blind image quality measure evaluate the improved performances of the proposed technique.     

The effect of Laplacian filter in adaptive unsharp masking for infrared image enhancement

Image processing, in particular image enhancement techniques have been the focal point of considerable research activity in the last decade. With the aid of an existing image enhancement technique, adaptive unsharp masking (AUM), we propose a novel kernel to be used in AUM filtering in order to enhance discontinuities which occur on the edges of targets of interest in infrared (IR) images. The proposed method uses an adaptive filter approach where an objective function is minimized by using descent algorithms. The output IR image has better sharpness and contrast adjustment for the detection of targets in terms of objective quality metrics. Hence, the proposed method ensures that the edges of the targets in IR images are sharper and that the quality of contrast adjustment has its optimum level in terms of peak signal-to-noise ratios.     

基于Retinex理论与概率非局部均值的红外图像增强方法

针对传统红外图像增强算法中细节模糊及过度增强的问题,提出了一种基于Retinex理论与概率非局部均值相结合的红外图像增强方法.首先通过单尺度Retinex方法调整图像中过暗与过亮部分的灰度级;然后利用概率非局部均值对图像进行分解处理得到基本层与细节层,对基本层采用直方图均衡化拉伸对比度,对细节层采用非线性函数进行增强;最后,将不同层次的结果融合得到对比度与细节增强的红外图像.用该方法对多组不同场景的红外图像进行仿真实验,并将其与多种增强方法进行主、客观对比分析,结果表明所提方法在红外图像的细节及对比度增强方面都获得了更好的效果.     

基于小波变换的激光主动成像图像去噪方法

 针对激光主动成像图像的特点,提出了将小波变换和中值滤波相结合的图像去噪方法。在对小波分解后的水平、垂直和对角3个方向高频细节图像进行处理时,我们采用3种不同形状的模板进行均值滤波,为了保护图像的边缘和细节信息,采用边缘检测法来将高频中的边缘细节与噪声分开。实验结果表明:该方法在降低图像噪声的同时又较好地保留了图像的细节,去噪效果比较理想。     

Gaussian mixture model-based gradient field reconstruction for infrared image detail enhancement and denoising

Infrared images are characterized by low signal-to-noise ratio and low contrast. Therefore, the edge details are easily immerged in the background and noise, making it much difficult to achieve infrared image edge detail enhancement and denoising. This article proposes a novel method of Gaussian mixture model-based gradient field reconstruction, which enhances image edge details while suppressing noise. First, by analyzing the gradient histogram of noisy infrared image, Gaussian mixture model is adopted to simulate the distribution of the gradient histogram, and divides the image information into three parts corresponding to faint details, noise and the edges of clear targets, respectively. Then, the piecewise function is constructed based on the characteristics of the image to increase gradients of faint details and suppress gradients of noise. Finally, anisotropic diffusion constraint is added while visualizing enhanced image from the transformed gradient field to further suppress noise. The experimental results show that the method possesses unique advantage of effectively enhancing infrared image edge details and suppressing noise as well, compared with the existing methods. In addition, it can be used to effectively enhance other types of images such as the visible and medical images.