基于形态学变换和FFCM聚类的灰度图像颜色迁移算法

针对传统颜色迁移算法计算量大、对图像无法准确进行颜色迁移的问题,提出一种基于形态学变换和快速模糊C均值聚类（FFCM）的灰度图像颜色迁移算法。首先对目标图像进行腐蚀膨胀运算,消除亮度不均匀的区域,通过FFCM聚类算法对目标图像进行准确聚类,然后在目标图像与源图像中选取对应样本块,完成样本块的颜色迁移,并以已上色的样本块为参考,完成图像的全局颜色迁移。实验结果表明:与Welsh和FCM算法相比较,本文算法处理时间分别缩短64.29 %和54.25 %,结果图像在类间交界处的颜色过渡更加自然,证明了算法的有效性。     

多算法融合的自适应图像增强方法

提出一种多算法融合的图像增强方法,用于工程应用中的复杂降质图像的细节特征恢复.该方法汲取了Laplacian变换法、Sobel梯度法、盒状滤波法、非锐化掩蔽法及灰度幂律法等算法的优点,可对模糊图像进行自适应增强.通过拉普拉斯滤波器和梯度滤波器将原始图像分为基础层、细节层及边缘特征层;对微小细节信息及边缘特征信息进行增强,对基础信息进行压缩;然后采用盒装滤波器对图像的三个分层进行平滑过度及噪音过滤,最后使用非锐化掩蔽法和灰度变换来增加图像灰度的动态范围,从而得到增强后的图像.在相同的工况下,该方法分别与直方图均衡法、自适应伽马矫正法及小波变换的图像增强法实验结果进行对比,结果表明,该方法将图像的清晰度提高了13.1%~126.1%,能有效地处理复杂型感染的图像,避免图像过度增强,可以获得适合人眼的最佳视觉细节内容的增强效果.     

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.     

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.     

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LLE的红外成像彩色化处理算法研究

针对红外图像对比度低、细节较差,且一般是黑白图像,不适宜于人眼观察,提出一种利用局部线性映射方法（LLE）的红外成像彩色化方法。该方法寻求灰度空间到色彩空间的映射,实现红外图像到彩色红外图像的转变,先将目标红外图像和彩色模板图像转换至YUV颜色空间,分离亮度和色彩信息;然后将目标红外图像的每个像素及邻域像素的灰度值串接成矢量,并均匀从彩色模板图像选取部分像素按相同方法串接成矢量,采用欧氏距离搜索最近邻并计算最佳的匹配系数,经色彩值（即U和V分量）计算将模板图像的彩色传递给目标红外图像后搜索亮度最大值的像素邻域并经自动阈值伪彩色编码处理,突出显示重要目标,得到处理后的彩色红外图像。将算法应用于实验室自主开发的热像仪,算法作用后的红外图像不但有了适于人眼视觉的彩色信息,而且用红、黄等敏感色突出了重点热目标,提高了人眼发现和识别目标的速度,实验结果表明,算法有利于侦察人员长时间的目标观察和识别目标。     

Infrared image enhancement with learned features

Due to the variation of imaging environment and limitations of infrared imaging sensors, infrared images usually have some drawbacks: low contrast, few details and indistinct edges. Hence, to promote the applications of infrared imaging technology, it is essential to improve the qualities of infrared images. To enhance image details and edges adaptively, we propose an infrared image enhancement method under the proposed image enhancement scheme. On the one hand, on the assumption of high-quality image taking more evident structure singularities than low-quality images, we propose an image enhancement scheme that depends on the extractions of structure features. On the other hand, different from the current image enhancement algorithms based on deep learning networks that try to train and build the end-to-end mappings on improving image quality, we analyze the significance of first layer in Stacked Sparse Denoising Auto-encoder and propose a novel feature extraction for the proposed image enhancement scheme. Experiment results prove that the novel feature extraction is free from some artifacts on the edges such as blocking artifacts, “gradient reversal”, and pseudo contours. Compared with other enhancement methods, the proposed method achieves the best performance in infrared image enhancement.     

近红外与可见光双通道传感器信息融合的去雾技术

为了对雾霾天气下的图像进行去雾处理,多幅图像去雾算法是常用的方法之一。多幅图像去雾算法也有多种形式,部分算法面临硬件实现困难、获取途径受限或者可实施性弱等问题,而且多幅图像比对处理时常常涉及图像配准,造成算法的实时性差、计算复杂度高等问题。针对以上问题,提出的算法为多幅图像去雾提供了新的思路,基于双目传感器硬件架构能够同时捕获近红外和可见光图像,将近红外传感器图像作为新的数据源,近红外传感器能够在一定程度上穿透雾霾,在雾天捕获可见光传感器无法捕获的图像细节,而且硬件实现简单。可见光图像的颜色信息较丰富,近红外传感器图像对近处场景细节的描述能力较好,捕获的图像稍加校正就能实现完全配准,将近红外图像与可见光图像进行融合,在去雾的同时,可以将近红外传感器图像中的原始细节提取融合到彩色可见光传感器图像中,得到边缘、轮廓等细节信息更加丰富的去雾图像。基于上述思路,借助近红外传感器对边缘细节的描述能力和可见光传感器对颜色信息的反映能力,提出了一种基于近红外与可见光双通道传感器图像融合的去雾算法。首先,将彩色可见光图像转换到HIS彩色空间,分别得到亮度通道图像、色调通道图像和饱和度通道图像。先将其亮度通道图与近红外图像进行融合去雾处理。采用非下采样Shearlet变换（NSST）进行分解,对得到的高频系数进行双指数边缘平滑滤波器保边滤波处理,对低频系数进行反锐化掩蔽处理,通过融合规则和反向变换得到新的亮度通道图像。然后,在对可见光图像的色彩处理中,建立饱和度图的退化模型,采用暗原色原理对参数进行估计,得到估计的饱和度图。最后,将新的亮度通道图像,估计的饱和度图像和原色调图像反映射到RGB空间得到去雾图像。为了验证新算法的有效性,特选取四组雾天拍摄的真实近红外图像与可见光图像进行融合去雾处理,将融合结果与其他两种去雾方法对于彩色可见光图像的去雾效果进行比较。实验结果表明,该算法在提高图像的边缘对比度和视觉清晰度上有较好的效果。并提出将近红外传感器图像作为新的数据源,采用双通道图像融合方法进行去雾处理,为图像去雾提供的新的技术思路是可行的。该算法的优势在于：首先提出将图像融合方法与去雾算法相结合,得到了新的去雾算法的思路。将彩色可见光图像转换到HSI色彩空间,将其亮度通道图与近红外图像采用非下采样Shearlet变换方法进行融合处理,在去雾的同时,可以将近红外传感器图像中的原始细节提取融合到彩色可见光传感器图像中,使得去雾图像中的边缘、轮廓等细节信息更加丰富。其次,提出了在图像去雾算法中采用新的数据源--近红外传感器图像,从图像处理的角度,近红外传感器能够在一定程度上穿透雾霾,对于近处场景细节的描述能力较好,而且硬件实现简单,捕获的图像稍加校正就能实现完全配准,为后续的融合去雾算法带来了便利,为图像去雾提供了新的技术途径和路线。再次,采用的是多幅图像去雾算法,该算法基于双目传感器获取图像,可见光图像的颜色信息较丰富,近红外图像对于近处场景细节的描述能力较好,相对于单幅图像去雾算法,有更好的效果。最后,将可见光传感器图像映射到其他色彩空间,对于每个通道的图像根据其特征有针对性地进行处理。可见光图像的亮度通道图和近红外图像的处理采用了图像融合和增强处理,对于可见光图像饱和度通道的处理采用了图像复原算法,可以从整体上提升去雾效果,对细节特征有了进一步增强。该算法为图像去雾提供了新的技术途径和路线。     

Image enhancement algorithm based on improved lateral inhibition network

There is often substantial noise and blurred details in the images captured by cameras. To solve this problem, we propose a novel image enhancement algorithm combined with an improved lateral inhibition network. Firstly, we built a mathematical model of a lateral inhibition network in conjunction with biological visual perception; this model helped to realize enhanced contrast and improved edge definition in images. Secondly, we proposed that the adaptive lateral inhibition coefficient adhere to an exponential distribution thus making the model more flexible and more universal. Finally, we added median filtering and a compensation measure factor to build the framework with high pass filtering functionality thus eliminating image noise and improving edge contrast, addressing problems with blurred image edges. Our experimental results show that our algorithm is able to eliminate noise and the blurring phenomena, and enhance the details of visible and infrared images.     

可见光与红外彩色融合图像感知清晰度评价模型

提出了感知清晰度评价模型,来评价人眼对红外与可见光彩色融合图像细节和边缘的可辨识度。首先,利用人眼对比度敏感函数模型,抑制在特定观察条件下图像中人眼不敏感的频率成分。之后,在局部频带对比度模型基础上,结合人眼亮度掩模特性构造了感知对比度模型。最后,计算融合图像人眼兴趣区域(细节和边缘区域)的感知对比度,进而评价融合图像的感知清晰度。实验结果表明,与现有的五种彩色图像清晰(模糊)度的客观评价模型相比,考虑人眼视觉特性感知清晰度模型的计算结果与人眼主观感受具有较好的一致性,可以有效地对彩色融合图像清晰度进行客观评价。     

基于神经网络的低照度彩色图像增强算法

由于低照度彩色图像存在整体亮度低、对比度低、颜色偏暗和信噪比低等特点,所以经典图像增强算法对其增强效果非常有限。提出了一种利用BP神经网络进行彩色图像增强的算法,并将RGB图像转换成HSI图像,以保证增强处理不引起图像的色彩失真。实验证明:该方法显著地改善了低照度彩色图像的视觉效果,提高了图像整体亮度和图像的信噪比,可调节图像的动态范围,能增强图像的对比度和细节,可增加图像信息熵。     

A new adaptive contrast enhancement algorithm for infrared images based on double plateaus histogram equalization

In infrared images, detail pixels are easily immerged in large quantity of low-contrast background pixels. According to these characteristics, an adaptive contrast enhancement algorithm based on double plateaus histogram equalization for infrared images was presented in this paper. Traditional double plateaus histogram equalization algorithm used constant threshold and could not change the threshold value in various scenes, so that its practical usage is limited. In the proposed algorithm, the upper and lower threshold value could be calculated by searching local maximum and predicting minimum gray interval and be updated in real time. With the proposed algorithm, the background of infrared image was constrained while the details could also be enhanced. Experimental results proved that the proposed algorithm can effectively enhance the contrast of infrared images, especially the details of infrared images.     

基于BIRCH聚类加速的彩色图像增强算法

针对现存的大多图像增强算法增强的图像可见性丢失问题,提出了一种基于BIRCH聚类加速的彩色图像增强算法;首先,通过BIRCH聚类加速确定数据库中与输入图像直方图相似度最高的图像来提取图像特征;然后,选择最小欧氏距离的特征值进行图像融合以获取目标图像;最后,增强图像通过目标图像直方图规范化和后期处理获得;大量图像融合实验结果验证了算法的有效性,该算法扩展了图像增强的类别,解决了增强过程中可能出现的可见性丢失问题,使图像增强的适应性更强;另外,EM、CII和SSIM评估指标的结果表明该算法明显改善了增强效果。     

A new single-image fog removal algorithm based on physical model

Based on the physical model of atmospheric scattering and the optical reflectance imaging model, three major factors which affect the effect of fog removal are discussed in detail, dark channel phenomenon is explained via the optical model, and an approach for solving the parameter in the atmospheric scattering model is rigorously derived from a new perspective. Using gray-scale opening operation and fast joint bilateral filtering techniques, the proposed algorithm can effectively obtain the global atmospheric light and greatly improve the speed and accuracy of atmospheric scattering function solving. Finally, the scene albedo is recovered by inverting this model. Compared with existing algorithms, complexity of the proposed method is only a linear function of the number of input image pixels and this allows a very fast implementation. The simulation results show that the processing time of images with a resolution of 576*768 is only 1.7 s; Results on a variety of outdoor foggy images demonstrate that the proposed method achieves good restoration for contrast and color fidelity, resulting in a great improvement in image visibility.     

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。     

Infrared image enhancement using Cellular Automata

Image enhancement is a crucial technique for infrared images. The clear image details are important for improving the quality of infrared images in computer vision. In this paper, we propose a new enhancement method based on two priors via Cellular Automata. First, we directly learn the gradient distribution prior from the images via Cellular Automata. Second, considering the importance of image details, we propose a new gradient distribution error to encode the structure information via Cellular Automata. Finally, an iterative method is applied to remap the original image based on two priors, further improving the quality of enhanced image. Our method is simple in implementation, easy to understand, extensible to accommodate other vision tasks, and produces more accurate results. Experiments show that the proposed method performs better than other methods using qualitative and quantitative measures.     

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。     

Low Light Image Enhancement Algorithm Based on Detail Prediction and Attention Mechanism

Most LLIE algorithms focus solely on enhancing the brightness of the image and ignore the extraction of image details, leading to losing much of the information that reflects the semantics of the image, losing the edges, textures, and shape features, resulting in image distortion. In this paper, the DELLIE algorithm is proposed, an algorithmic framework with deep learning as the central premise that focuses on the extraction and fusion of image detail features. Unlike existing methods, basic enhancement preprocessing is performed first, and then the detail enhancement components are obtained by using the proposed detail component prediction model. Then, the V-channel is decomposed into a reflectance map and an illumination map by proposed decomposition network, where the enhancement component is used to enhance the reflectance map. Then, the S and H channels are nonlinearly constrained using an improved adaptive loss function, while the attention mechanism is introduced into the algorithm proposed in this paper. Finally, the three channels are fused to obtain the final enhancement effect. The experimental results show that, compared with the current mainstream LLIE algorithm, the DELLIE algorithm proposed in this paper can extract and recover the image detail information well while improving the luminance, and the PSNR, SSIM, and NIQE are optimized by 1.85%, 4.00%, and 2.43% on average on recognized datasets.     

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,而且色彩自然、不失真且运行速度快.     

Infrared image detail enhancement based on local adaptive gamma correction

An infrared image detail enhancement method based on local adaptive gamma correction (LAGC) is proposed. The local adaptive gamma values are designed based on the Weber curve to enhance effectively the image details. Subsequently, the active grayscale range of the image processed by LAGC is further extended by using our proposed histogram statistical stretching. The experimental results show that the proposed algorithm could considerably increase the image details and improve the contrast of the entire image. Thus, it has significant potential for practical applications.