基于主特征提取的Retinex多谱段图像增强

根据Retinex视觉模型中照射分量和反射分量的统计特性,融合多尺度主特征提取法、平台直方图算法、非局部均值滤波及局部细节增强算法可对多谱段图像进行有效增强.首先利用多尺度主特征提取法估计照射分量,对照射分量进行平台直方图操作,增强全局对比度及图像主结构边缘细节;然后将原图与照射分量相除获取反射分量,对反射分量进行非局部均值滤波抑制噪声,再进行基于局部方差的局部细节增强;最后将增强后的照射分量与反射分量相乘,即为增强图像.从主观和客观两方面,对X光图像、紫外图像、可见光图像、低照度可见光图像和红外图像实验结果的分析表明,本文算法能够有效地抑制图像噪声、增强图像对比度及细节、改善图像视觉效果,是一种通用有效的多谱段图像增强算法.     

基于光照-反射成像模型和形态学操作的多谱段图像增强算法

为解决多谱段降质图像增强问题,提出了一种基于光照-反射成像模型和形态学操作的多谱段图像增强算法.首先对图像饱和度使用自适应非线性拉伸函数进行拉伸,使增强后的图像色彩更加饱和、自然;接下来利用引导滤波算法提取出图像的光照分量,提出了一种基于细节特征的加权融合策略,利用光照分布特性构造了一种自适应Gamma校正函数对光照分量进行处理,并将其与利用对比度受限的自适应直方图均衡化方法处理后的光照分量以及原始光照分量进行融合;然后在反射分量校正时,构造了一种形态学操作函数来校正反射信息;最后合并光照分量和反射分量,并与处理后的饱和度分量和色调分量一起得到增强图像.采用主客观评价指标对可见光低照度图像、水下图像、高动态范围图像、沙尘暴图像、雾天图像和热红外图像6种降质多谱段图像实验结果进行分析比较,结果表明本文算法能够有效地抑制图像噪声、增强图像细节信息、改善图像视觉效果,可应用于多种图像增强领域.     

一种基于单尺度Retinex的雾天降质图像增强新算法

雾图增强是智能管理系统的一个组成部分,在交通管理系统、公路收费站、轮船、飞机场等场合有着广泛的应用场景。比较了对数函数、双曲正切函数、反双曲正切函数对雾天降质图像亮度分量的调节能力,证明双曲正切函数具有比对数函数更宽的亮度调节能力。在此基础上提出一种基于单尺度Retinex的雾天图像增强方法。该算法首先把图像从RGB彩色空间转换到HSV空间,保持色调分量不变,采用中心可自适应调节的双曲正切函数增强图像的全局亮度,局部细节非线性变换处理进一步提高图像的局部对比度,运用线性拉伸对饱和度进行调整,实现颜色补偿。实验结果表明该方法去雾效果显著,且颜色自然。实验还结合方差、熵和算法运算时间等参数,对该算法与多尺度Retinex算法作比较,验证了该算法在图像对比度、细节增强方面的优越性,且算法速度快,具有应用于实时图像处理的能力。     

融合Retinex和离散小波奇异值分解的远距离目标图像清晰化

针对远距离成像系统获取的低照度降质图像增强问题,提出了一种融合Retinex和离散小波奇异值分解的图像清晰化算法。该方法首先利用自适应全尺度Retinex（adaptive full-scale retinex, AFSR）“粗”提取照度分量和反射分量,然后通过离散小波变换将所提取的图像反射分量分解为4个频率子带并估计出低频子带图像的奇异值矩阵,最后应用逆小波变换“精”重建图像。实验结果表明:所提方法处理后的低照度降质图像视觉增强效果较好,在图像对比度、信息熵、平均梯度和边缘密度等客观评价指标方面优于其他经典算法。     

修正Retinex照射反射模型的彩色图像增强

介绍了修正Retinex照射反射模型的彩色图像增强方法,引入了非线性变换函数修正彩色图像的照射分量和反射分量。由于全局对比度增强函数能够拉伸图像的照射分量,所以改善了全局视觉效果。非线性S型函数对较大和较小的反射分量值改变较小,对中间值改变较大,从而改善了图像的局部对比度。在RGB彩色空间和其他色度亮度彩色空间中的处理结果都没有出现彩色失真的现象。     

基于多尺度Retinex的非下采样Contourlet域图像增强

针对部分遥感图像和高光谱图像中存在的对比度不足、整体偏暗等问题,提出了一种基于多尺度Retinex(MSR)和混沌小生境粒子群优化(NCPSO)的非下采样Contourlet变换(NSCT)域图像增强方法,用于改善图像质量。对图像进行NSCT分解,得到一个低频分量和多个不同方向的高频分量;在低频分量上进行混合灰度函数的多尺度Retinex增强;同时利用非线性增益函数调整高频分量系数,将兼顾对比度和信息熵的定量综合评价函数作为NCPSO的适应度,寻找非线性增益函数所涉及的最优参数。大量实验结果表明,与双向直方图均衡方法、NSCT方法、多尺度Retinex方法、平稳小波变换和Retinex方法等4种增强方法相比,提出的方法能更有效地提高图像的对比度和信息熵,增强图像的整体视觉效果。     

基于迭代直方图均衡化的常规光源下水下成像增强算法

为了增强常规光源下水下图像的视觉对比度,提高水下图像的图像质量,提出一种基于迭代直方图均衡化水下图像增强算法.首先通过Retinex模型将水下图像分解为细节层和光照层图像.然后推导出一个图像增强模型,该模型能够在保证韦伯对比度的前提下完成图像增强工作.接着提出一种基于迭代直方图的直方图均衡化算法对光照层图像进行对比度增强,并通过S形状函数对细节层图像进行对比度拉伸.最后,合并拉伸后的细节层图像和增强后的光照层图像,进而获得较佳的图像增强效果.实验结果表明,该算法能够有效地提升水下图像的视觉对比度,图像信息熵值及均值结构相似度高于其他算法,图像的视觉效果得到显著提高.     

基于深度卷积神经网络的低照度图像增强

针对低照度条件下图像降质严重的问题,提出了一种基于深度卷积神经网络(DCNN)的低照度图像增强算法。该算法根据Retinex模型合成训练样本,将原始低照度图像从RGB (Red Green Blue)空间转换到HSI (Hue Saturation Intensity)颜色空间,保持色度分量和饱和度分量不变,利用DCNN对亮度分量进行增强,最后将HSI颜色空间转换到RGB空间,得到最终的增强图像。实验结果表明,与现有主流的图像增强算法相比,所提算法不仅能够有效提升亮度和对比度,改善过增强现象,而且能够避免色彩失真,主观视觉和客观评价指标均得到了进一步提高。     

一种使用混合智能优化算法的图像增强方法

对比度增强在图像处理系统中常用来提高降质图像质量或增强图像细节。从优化问题的角度来处理图像增强,提出了用混合智能算法,结合细菌觅食优化算法和粒子群优化算法的优点,对图像增强算子的参数进行优化,使图像质量达到最佳。使用的增强算子取决于源图像的局部灰度信息和全局统计信息,采用的适应度函数是基于图像的边缘信息和熵信息。仿真和实验结果表明该方法不仅能实现图像对比度增强还能有效提高目标图像的细节,并有效抑制噪声。     

基于色调恒定的MSR图像增强算法

由于多尺度Retinex算法增强后图像存在细节信息减弱和颜色失真等不足,本文提出了一种色调恒定的图像增强算法.在原图像中去掉用多尺度高斯函数估计的光照分量,结合参量自适应的非线性函数调整亮度,依据色调恒定的理论保持增强后图像的颜色.与多尺度Retinex比较的实验结果表明,本文算法更有效,增强后的图像不仅细节清晰,而且...     

基于双边纹理滤波的图像细节增强方法

为了实现图像的细节增强,特别是纹理细节增强,同时尽可能保持图像的结构完整,提出了一种基于双边纹理滤波的图像多尺度分解方法。首先,对图像进行多尺度双边纹理滤波分解,分别得到一幅基本图像和一系列细节纹理图像。接着,类似于小波增强方法,对细节图像采用多尺度自适应增强方法,得到一系列增强后的纹理细节图像。最后,将基本图像和增强后细节图像相加,重构出最后的增强图像。实验结果表明:本文提出的增强方法能够在突出边缘的同时,较好地增强图像中的纹理细节信息。将基于双边纹理滤波的多尺度分解引入图像增强,能更好地体现图像纹理细节特征,为增强图像提供更加丰富的信息。     

Infrared image enhancement through saliency feature analysis based on multi-scale decomposition

To improve contrast between dim target region and background in infrared (IR) long-range surveillance, this paper proposes a fast image enhancement approach using saliency feature extraction based on multi-scale decomposition. Firstly, a smooth based multi-scale decomposition is designed and applied to original infrared image, generating sub-images with various frequency components at different decomposition levels. The dim target regions of sub-images are extracted by a local frequency-tuned based saliency feature detection method, secondly. With saliency maps created by saliency extraction using multi-scale local windows with different sizes, the sub-images are enhanced at different decomposition scales. Finally, the enhanced result is reconstructed by synthesizing the all sub-images with adjustable synthetic weights. Since salient areas are analyzed based on fast multi-scale image decomposition, IR image can be s enhanced with good contrast successfully and rapidly. Compared with other algorithms, the experimental results prove that the proposed method is robust and efficient for IR image enhancement.     

Synthetic Aperture Radar image nonlinear enhancement algorithm based on NSCT transform

Due to the imaging mechanism, Synthetic Aperture Radar (SAR) images are susceptible to speckle noise, which affects radar image interpretation. So image denoising and enhancement are important topics of improving SAR image performance. A nonlinear image enhancement algorithm based on nonsubsampled contourlet transform (NSCT) is proposed in this paper. The image is decomposed into coefficients of different scales and directions through nonsubsampled contourlet transform. It is denoised by the threshold method of the multi-scale product of NSCT coefficients. Then thresholds of the nonlinear enhancement function are determined according to the coefficients of each scale. The two parameters of the function, among which one is used to control the range of enhancement and the other can determine the strength of enhancement, are obtained by solving nonlinear equations. The coefficients processed by the enhancement function are used to reconstruct the image. The simulation results on the Matlab platform show that the algorithm has a good effect of enhancing details of images and suppressing noise signals meanwhile.     

基于YCbCr颜色空间的Retinex低照度图像增强方法研究

针对Retinex理论的低照度图像增强算法中光照图像估计问题,提出一种基于YCbCr颜色空间的低照度图像增强方法.该方法将原始低照度图像从RGB(Red Green Blue)颜色空间转换到YCbCr颜色空间,提取该空间中Y分量构建为原始光照图像分量L1(x,y),并对L1(x,y)进行Gamma校正得到增强的光照图像分量L2(x,y),经Retinex模型得到增强图像R(x,y),采用多尺度细节增强方法对图像R(x,y)进行细节增强,得到最终增强图像Re(x,y).实验结果表明,所提方法不仅能有效提升亮度,避免亮度和色彩失真,增强了图像的细节信息并获得了更好的视觉效果,而且运行速度快.     

Fast image enhancement using multi-scale saliency extraction in infrared imagery

We propose a multi-scale saliency extraction based fast infrared image enhancement approach. A local frequency-tuned based saliency extraction technique is designed for highlighting the salient regions, firstly. Then, multi-scale saliency extraction is demonstrated, introducing multi-scale local windows with different sizes to extract regions of interest at different scales. Finally, the original image is enhanced with combining multi-scale salient image regions into one image. The experimental results prove the proposed approach is robust and efficient for infrared image enhancement.     

基于优势特征图像融合的水下光学图像增强

针对水下光学图像颜色失真、非均匀光照、对比度低的问题,提出基于优势特征图像融合的水下光学图像增强算法.首先,提出改进的暗通道先验算法去除退化图像中的不均匀浑浊并均衡色彩;其次,对颜色校正图像分别使用基于加权分布的自适应伽玛校正算法和限制对比度自适应直方图均衡-同态滤波算法,增强颜色校正图像对比度并使其亮度均衡;最后,定义三幅融合图像即颜色校正图像、亮度均衡图像、对比度增强图像的关联权重图,通过多尺度融合算法获得融合图像.与单一预处理算法只能解决对应的退化现象相比,该算法对单幅退化图像进行多算法处理,得到三幅优势特征图像,通过不同权重的组合最大程度地将各优势特征相结合,得到的综合效果远超各单一算法优化效果,不再局限于解决颜色失真等单一问题.将本文算法与现有算法在主观评价和客观评价两方面进行实验对比,结果表明,该算法可以有效平衡水下图像的色度、饱和度及清晰度,视觉效果接近自然场景下的图像.     

Fusion of the low-light-level visible and infrared images for night-vision context enhancement

For better night-vision applications using the low-light-level visible and infrared imaging, a fusion framework for night-vision context enhancement(FNCE) method is proposed. An adaptive brightness stretching method is first proposed for enhancing the visible image. Then, a hybrid multi-scale decomposition with edge-preserving filtering is proposed to decompose the source images. Finally, the fused result is obtained via a combination of the decomposed images in three different rules. Experimental results demonstrate that the FNCE method has better performance on the details(edges), the contrast, the sharpness, and the human visual perception. Therefore,better results for the night-vision context enhancement can be achieved.     

Fusion of visible and infrared images using saliency analysis and detail preserving based image decomposition

Image fusion for visible and infrared images is a significant task in image analysis. The target regions in infrared image and abundant detail information in visible image should be both extracted into the fused result. Thus, one should preserve or even enhance the details from original images in fusion process. In this paper, an algorithm using pixel value based saliency detection and detail preserving based image decomposition is proposed. Firstly, the multi-scale decomposition is constructed using weighted least squares filter for original infrared and visible images. Secondly, the pixel value based saliency map is designed and utilized for image fusion in different decomposition level. Finally, the fusion result is reconstructed by synthesizing different scales with synthetic weights. Since the information of original signals can be well preserved and enhanced with saliency extraction and multi scale decomposition process, the fusion algorithm performs robustly and excellently. The proposed approach is compared with other state-of the-art methods on several image sets to verify the effectiveness and robustness.