Multichannel image contrast enhancement based on linguistic rule-based intensificators

This study follows the direct approach to image contrast enhancement, which changes the image contrast at each its pixel and is more effective than the indirect approach that deals with image histograms. However, there are only few studies following the direct approach because, by its nature, it is very complex. Additionally, it is difficult to develop an effective method since it is required to keep a balance in maintaining local and global image features while changing the contrast at each individual pixel. Moreover, raw images obtained from many sources randomly influenced by many external factors can be considered as fuzzy uncertain data. In this context, we propose a novel method to apply and immediately handle expert fuzzy linguistic knowledge of image contrast enhancement to simulate human capability in using natural language. The formalism developed in the study is based on hedge algebras considered as a theory, which can immediately handle linguistic words of variables. This allows the proposed method to produce an image contrast intensificator from a given expert linguistic rule base. A technique to preserve global as well as local image features is proposed based on a fuzzy clustering method, which is applied for the first time in this field to reveal region image features of raw images. The projections of the obtained clusters on each channel are suitably aggregated to produce a new channel image considered as input of the pixelwise defined operators proposed in this study. Many experiments are performed to demonstrate the effect of the proposed method versus the counterparts considered.     

基于最优模糊变换和Retinex理论的静脉图像增强方法

一种新的结合模糊变换和retinex理论静脉图像增强方法,可以解决近红外静脉图像所存在的低对比度,动态范围狭窄和强度分布不对称问题。最优模糊变换用于加强全局对比度,引入的Retinex方法可以增强图像细节信息,弥补最优模糊变换的细节缺失。由于图像从空间域向模糊域转换时使用一个参数优化隶属函数,处理的图像不具有最佳性,文中提出一种双参数的隶属函数的优化方法,同时提出一种自适应的选择控制参数方法。实验结果表明,该方法可以有效提高静脉图像与背景的对比度,与其他方法的实验结果相比较,可以看出该办法具有更好的图像增强性能。     

一种直接图像增强方法在医学影像分类中的应用

针对乳腺X线照片中所蕴含信息的特征提出采用一种新颖的直接同质增强方法来实现图像增强,算法与传统的直方图均衡化方法不同,既考虑了图像的局部区域又兼顾了图像的全局信息,从而可以在增强图像的同时又保留了图像中有用的信息.将算法作为预处理部分应用到乳腺X线照片的分类系统中,得到了较好的效果.     

一种基于图象分割的增强算法

图象增强作为图象处理常用的工具,目的是为了消除原因图象图象边缘模糊,对比度差等缺点,增强图象的视觉效果和加以后的处理工作提供方便,文中提出的算法基于Ｈａｒａｌｉｃｋ的斜模型和Ｂｅｇｈｄａｄｉ的对比度增强算法。     

Segment dependent dynamic multi-histogram equalization for image contrast enhancement

Histogram equalization (HE) method proved to be a simple and most effective technique for contrast enhancement of digital images. However it does not preserve the brightness and natural appearance of the images, which is a major drawback. To overcome this limitation, several Bi- and Multi-HE methods have been proposed. Although the Bi-HE methods significantly enhance the contrast and may preserve the brightness, the natural appearance of the images is not preserved as these methods suffer with the problem of intensity saturation. While Multi-HE methods are proposed to further maintain the brightness and natural appearance of images, but at the cost of contrast enhancement. In this paper, two novel Multi-HE methods for contrast enhancement of natural images, while preserving the brightness and natural appearance of the images, have been proposed. The technique involves decomposing the histogram of an input image into multiple segments based on mean or median values as thresholds. The narrow range segments are identified and are allocated full dynamic range before applying HE to each segment independently. Finally the combined equalized histogram is normalized to avoid the saturation of intensities and un-even distribution of bins. Simulation results show that, for the variety of test images (120 images) the proposed method enhances contrast while preserving brightness and natural appearance and outperforms contemporary methods both qualitatively and quantitatively. The statistical consistency of results has also been verified through ANOVA statistical tool.     

红外图像全局和局部对比度增强的非线性增益法

提出一种基于模拟退火算法和离散平稳小波变换增强红外图像全局和局部对比度的非线性增益算法.基于原始红外图像的灰度直方图提出一种判据,利用该判据判断原始红外图像的对比度类型,以指导模拟退火算法的搜索方向和初值的选取;并利用模拟退火算法优化非线性灰度变换参数,实现对图像进行全局对比度增强.对全局增强后的图像进行离散平稳小波变换,分别对各个分解层的高频子带利用所提出的非线性增强算法进行细节增强.实验结果表明,该算法在有效地提高红外图像整体对比度的同时,能突出红外图像中目标的细节部分信息,在视觉质量上优于传统的直方图均衡法、反锐化掩膜法等.     

基于第二代Curvelet变换的低对比度图像增强

针对传统图像增强方法用于低对比度图像时,存在对噪声敏感、局部过增强等问题,提出了一种基于第二代 Curvelet 变换的增强方法。将图像进行多尺度多方向的 Curvelet 变换;引入分段非线性函数的思想,调整低频子带系数,提高图像整体的对比度;对各尺度的高频子带系数进行非线性加权,增强图像细节,并进行阈值降噪。实验表明,该方法优于常用的空间域直方图均衡化和小波域图像增强法,能有效地提高图像的对比度、降低噪声,并且较好地保留边缘信息,具有良好的视觉效果。     

数字媒体图像多特征反差增强方法仿真

由于图像在生成的过程中会有相对的噪声产生,而噪声会直接影响该图像中的多特征信息,导致信息表达不完全等情况。基于此提出了数字媒体图像多特征反差增强方法。首先将需要对受噪声污染的图像进行去噪;其次运用偏微分方程(PDE)方法,构建出一种PDE数学模型-TV模型,在对图像去噪的同时,保持原图像的边缘轮廓信息,并且运用Split Bregman算法,并引入辅助变量转换出分段线性函数的泛函极值;在偏微分方程的基础上,运用改进后的反差增强方法,根据直方图的均衡化结果利用累积分布函数的方法,来当做图像灰度的变换函数,以达到合理的调整固定动态范围,且让图像整体视觉效果增强、提高图像中多特征信息的目的。通过仿真结果可以得知,提出的方法可以处理图像中噪声的影响,并且可以将图像中的多特征信息进行有效的反差增强处理,且具有直方图均衡化结果优秀、图像特征增强效率的优点。     

A real-time image processor with combining dynamic contrast ratio enhancement and inverse gamma correction for PDP

Inverse gamma correction must be performed before displaying the received video signal because alternating current plasma display panel (AC PDP) has a linear output luminance response to a digital-valued input. At the same time contrast ratio enhancement is necessary for improving the image quality of display devices. The histogram equalization (HE) is an important contrast ratio enhancement method. But sometimes HE can produce unrealistic effects in images. In this paper, a new method of combining dynamic contrast ratio enhancement and inverse gamma correction for AC PDP is proposed. The dynamic contrast ratio enhancement and the inverse gamma correction are realized simultaneously in the proposed method. Furthermore the over-enhancement caused by the traditional HE can be avoided. A real-time image processor with the proposed method was designed and implemented. Simulations and experimental results on a 50-in. AC PDP show that the image quality of AC PDP can be improved obviously.     

CLAHE和细节放大相结合的档案图像增强方法

图像增强可提高扫描档案图像的质量,关系到档案图像信息系统的生命。运用CLAHE可以进行全局对比度拉伸,运用Lee滤波器可进行局部细节放大,将两者结合可形成放大细节的CLAHE方法。对结合的方法从两方面进行改进,一是引入噪声抑制措施,使得Lee滤波器只放大图像细节而不放大噪声;二是制定柔性细节放大机制,使得细节放大更加符合人类视觉习惯。改进后的方法既能提高全局对比度,又能有效放大局部细节。实验表明,提出的方法对包含文本、图形和图像的扫描档案具有较好的增强效果,且能够满足国家行业规范要求和实际应用需要。     

一种基于视觉特性的彩色图像增强算法

为了增强图像暗区域部分,基于人类视觉系统的全局和局部自适应调节原理,提出一种彩色图像增强方法。该方法主要包括全局自适应亮度调节、局部对比度增强和颜色恢复3个部分。全局亮度调节采用直方图非线性自适应拉伸来增强暗区域的亮度;局部对比度增强利用当前点与区域像素之间的关系,调节当前点的亮度,以增强图像局部对比度;通过一种自适应的非线性颜色恢复算法恢复图像色彩。通过大量图像对比实验分析表明,本文方法可以自适应有效快速地实现图像增强。     

一种新的红外图像复合增强算法

通过对现有图像增强算法的分析,提出了一种新的红外图像复合增强算法。该算法将同态增晰和直接对比度增强算法结合,使得图像中的局部信息与全局信息在增强时都能被利用。外场实验表明,处理后的图像具有明显的局部对比度增强效果,同时较好地保持了图像的原始面貌。     

一种面向交通场景的快速图像增强算法

为提高夜间图像的增强效果,针对具体的交通场景提出一种改进的图像增强算法。通过改进自适应对比度增强算法（ACE）中放大系数的自适应函数,算法能够有针对性地增强图像亮度较低和对比度较低的区域,防止图像过度增强,并且能够增强图像的细节,克服传统对比度增强算法的不足。实验结果表明,该算法增强效果显著,针对具体夜间交通场景图像处理速度快,自适应效果好,具有消除“振铃效应”、颜色保真和较好的保留并增强图像边缘和细节的能力。     

Assessing a cross-border logistics policy using a performance measurement system framework: the case of Hong Kong and the Pearl River Delta region

For the most rapidly growing economic entity in the world, China, a new logistics operation called the indirect cross-border supply chain model has recently emerged. The primary idea of this model is to reduce logistics costs by storing goods at a bonded warehouse with low storage cost in certain Chinese regions, such as the Pearl River Delta (PRD). This research proposes a performance measurement system (PMS) framework to assess the direct and indirect cross-border supply chain models. The PMS covers four categories including cost, time, quality and flexibility in the assessment of the performance of direct and indirect models. Furthermore, a survey was conducted to investigate the logistics performance of third party logistics (3PLs) at the PRD regions, including Guangzhou, Shenzhen and Hong Kong. The significance of the proposed PMS framework allows 3PLs accurately pinpoint the weakness and strengths of it current operations policy at four major performance measurement categories. Hence, this helps 3PLs further enhance the competitiveness and operations efficiency through better resources allocation at the area of warehousing and transportation.     

基于纹理度划分的医学图像可逆信息隐藏方法

针对目前具有对比度增强效果的可逆信息隐藏（RDH）算法大多受到嵌入率的影响,未能实现较好的对比度增强效果的问题,提出一种基于纹理度划分的医学图像可逆信息隐藏方法。首先,通过对比度拉伸的方法实现医学图像对比度增强;然后,再利用医学图像纹理度的自身特点,将医学图像划分为高、低两类纹理度等级,其中高纹理度等级构成医学图像的关键部分;最后,为了进一步增强高纹理度等级的对比度并保证信息嵌入率,对不同的纹理度等级像素采用不同的嵌入方法。为了与其他具有对比度增强效果的医学图像可逆信息隐藏算法比较载密图像的对比度增强效果,采用了针对对比度失真的无参考图像质量评价标准（NR-CDIQA）作为实验客观依据。实验结果表明,在不同嵌入率下,使用所提方法的载密图像的NR-CDIQA值更高,对比度增强效果更好。     

Image fuzzy enhancement algorithm based on contourlet transform domain

In order to solve the problems of low contrast, global darkness and noise amplification in some hyperspectral and remote-sensing images, a new image fuzzy enhancement method based on contourlet transform (CT) domain is proposed. The algorithm includes the following four steps. Firstly, the cyclic translation method is used to suppress the pseudo-Gibbs phenomenon caused by the lack of translation invariance of the CT. Secondly, a nonlinear gain function is designed to enhance and suppress the high-frequency coefficients adaptively. Meanwhile, the multi-scale Retinex with mixed gray function is used to process the low-frequency sub-band coefficients. Then, the inverse translation and linear averaging and the inverse CT are performed on the enhanced coefficients, and finally the improved fuzzy contrast is used to enhance the texture and edge of the image globally. The experimental results show that the proposed method can make the image texture details more prominent, and enhance the overall visual effect of the images. Furthermore, the absolute mean difference and PSNR of images are also greatly improved .

     

家装设计渲染图增强

目的 提出一种亮度、对比度、饱和度三要素与神经网络相结合的家装设计渲染图增强方法。方法 该方法分析了图像增强的3个要素：亮度、对比度和饱和度。算法从下列几个方面着手进行三要素的调节：1）根据原图饱和度和图像融合方法实现亮度和对比度增强;2）采用颜色矩阵实现饱和度增强;3）采用直方图均衡实现对比度进一步增强。这3个要素对图像增强的效果均有贡献,本文为三要素分别赋予一个权值,并引入神经网络方法,自动建立图像亮度分量均值、方差和饱和度分量均值、方差与三要素的权值系数的非线性映射关系。结果 根据图像本身的信息自动获取图像增强三要素的增强系数,实现家装设计渲染图的自适应增强。算法的有效性在不同程度偏灰暗的家装设计渲染图上得到了验证,并与几种经典方法进行了直方图、信息熵、平均对比度（AC）和平均灰度（AG）的定量比较。实验结果显示,本文算法实验结果的直方图具有很少的信息丢失和较好的特征保持,与遗传算法相比,信息熵提高了约0.2,AC值提高了约0.1,AG值提高了约15,本文算法在多数情况下评价指标优于改进的直方图方法。结论 通过对实验结果的直观评价与定量评价,证明与某些现有的方法相比,本文方法适用于不同程度偏灰暗的渲染图,具有较好的通用性,并能达到更优的渲染图像增强效果。     

提高形状测量精度的直接与间接反射分离方法

针对光学三维形状测量中间接反射的存在导致三维测量精度下降的问题,提出一种分离直接反射和间接反射的改进结构光投影方法。该方法反向利用直接反射和相互反射间的相位差异,以格雷码结构光为基础设计出相互相位差为90°的调制结构光,将它投射到被测物体,以此分离出直接反射和间接反射;并加上改进结构光的正-反投影,来检测结构光条纹图像中的结构光边缘亚像素定位。实验结果表明,该方法不仅有效地分离出了间接反射,而且提高了被测物体的三维测量精度,扩大了三维测量范围。     

基于粒子群优化的图像自适应增强方法

将免疫粒子群优化算法和非完全Beta函数结合,提出了一种自适应图像对比度增强方法.该免疫粒子群优化算法结合了粒子群优化算法具有的全局寻优能力和免疫系统的免疫信息处理机制,改善了粒子群优化算法摆脱局部极值点的能力.利用免疫粒子群优化算法自动搜索最佳的灰度变换参数,从而获得一条最佳的灰度变换曲线,实现对图像进行全局增强处理.实验结果表明,该算法不仅能有效地提高图像整体对比度和视觉效果,而且适合图像的自动化处理.     

基于相似度测量和模糊熵的矿井图像增强方法

为了提高煤矿井下图像的视觉效果,提出一种改进的基于相似度测量的增强算法和模糊熵理论相结合的方法.根据煤矿井下图像的特点,引入模糊熵,建立基于模糊熵测度的判别准则,尽量去除噪声干扰.改进隶属度函数的计算方法,充分提取图像中的分形维特征信息.通过改进对比度变换因子的计算方法,进一步增强图像局部对比度.实验结果表明,处理后的图像不会出现增强过度现象,具有较好地噪声抑制、明暗对比和保持图像细节,是一种有效地矿井图像增强方法.