基于暗原色先验的嵌入式图像增强系统

针对彩色直方图均衡化算法颜色易失真的缺点,提出了一种基于暗原色先验的快速图像增强算法。首先求取全局暗原色图,然后估计透过率图和大气光成分图,最后根据大气散射模型恢复出图像中所有像素的灰度值。结合实际应用,以高性能DSP芯片TMS320DM6437作为中央处理器,结合现场可编程门阵列FPGA构成外围电路逻辑控制,搭建了嵌入式高速图像增强处理平台。基于该平台用真实图像验证了本文提出的算法。实验结果表明,本系统在提高色彩和对比度的同时,有效地还原了场景中物体的颜色,获得了较好的增强效果,同时算法运行时间少,能够满足工程项目的要求。     

基于暗原色先验模型的水下彩色图像增强算法

针对在水下环境中,光的散射和衰减导致水下光学成像质量严重下降,图像对比度低、颜色失真的问题,提出了一种暗原色先验和基于通道直方图量化的颜色校正算法相结合的图像增强新方法。对于待增强的水下彩色图像,首先建立水下光学图像成像模型,并利用优化与改进的暗原色先验算法对图像进行去模糊,然后通过分析R、G、B三通道的累积直方图,对去模糊后的彩色图像各通道灰度值进行量化,实现图像的颜色校正。实验结果表明,提出的方法可以有效地消除了由于光的散射造成图像的模糊,有效提高了水下图像的视觉效果,恢复水下图像的颜色平衡。     

融合暗原色先验和稀疏表示的水下图像复原

由于水下图像成像过程中受光的散射、噪声干扰等因素影响,致使图像质量严重退化。为了去除模糊和抑制噪声,改善水下图像质量,该文提出一种融合暗原色先验和稀疏表示的水下图像复原新方法。该方法首先利用暗原色先验理论计算水下图像的暗原色,然后基于稀疏表示理论对暗原色进行去噪和优化,基于改进后的暗原色计算水体透射率和光照强度以计算最终复原结果,可以同时达到去模糊和去噪的良好效果。实验结果表明,提出的方法有效提高了图像的平均梯度和信息熵等图像像素,从而改善了图像的质量。     

基于暗原色先验的遥感图像云雾处理方法

遥感图像在近代科学研究、气象及天文学等各个领域中有着广泛的应用,但它普遍受到大气的散射和吸收的影响。这将使其在各领域中发挥的作用受到限制。本文将针对遥感图像的特点,对暗原色先验去雾方法进行改进,提出更适合现实情况的非均匀大气光估计方法,并实验验证该方法的有效性。     

基于暗原色先验去雾原理的红外图像伪彩化增强方法研究

根据雾天红外图像的分析和判读需要,提出了一种新的预处理方法---基于暗原色先验去雾原理及HIS空间的伪彩变换方法。该方法应用于雾天红外灰度图像的处理时,可以显著增强目标与背景之间的对比度。实验表明,该方法可以较好地对雾天红外图像进行增强与显示。与传统的图像增强方法相比,该方法更有利于在雾天条件下对掠海飞行目标及海面目标的红外图像进行分析与判读。     

嵌入式雾天降质图像对比度增强系统设计

设计了以高性能DSP芯片TMS320VC6418作为中央处理器、结合现场可编程门阵列(FPGA)构成外围电路逻辑控制的嵌入式高速图像增强处理平台,并实现了一种彩色图像对比度增强算法.首先将彩色图像从RGB空间转化为HIS空间,然后对亮度空间进行直方图均衡化处理,最后转化到RGB空间进行输出.利用真实图像验证了该系统,实验结果表明,该系统可以有效提高对比度.获得较好的增强效果,计算时间少,能够满足工程需要.     

一种改进的基于暗原色先验的雾天图像清晰化方法

为了提高雾天降质图像的清晰度,基于暗原色先验提出了一种改进的图像去雾方法。针对原算法对明亮区域敏感和运算量过大问题,首先提出天空区域自适应选择算法求取大气光强度,然后利用快速双边滤波算法修复透射率图,在保证去雾效果前提下大幅度降低了计算复杂度。针对去雾后的图像颜色较真实场景偏灰暗的问题,提出了一种简单有效的亮度调节方法。实验结果表明,该算法可以有效的消除灰白和明亮区域对大气光和透射率计算的影响,真实地复原场景的色彩和清晰度,同时,本文算法的时间复杂度与图像大小成线性关系,可以明显提升运算速度。     

基于小波的同态滤波器用于图像对比度增强

同态增晰可用于减少光照不均匀引起的图像降质,并对感兴趣的景物进行有效增强,本文提出一种基于波波的同态增晰方法,采用一种高通滤波器对小波分解系数进行处理,处理后图像的局部对比度增强效果明显,又能较好地保持图像的原始面貌。     

基于改进直方图均衡的红外图像对比度增强算法

针对红外图像灰度分布集中、对比度低的特征,提出了一种基于改进直方图均衡的对比度增强算法。首先采用线性对比度增强将原始16位红外图像映射到8位图像A;然后采用改进的平台直方图均衡将原始16位红外图像映射到8位图像B;再根据输入图像的灰度级范围动态确定映射图像A和B的权值;最后以确定的权值将映射图像A和B合并,得到最终对比度增强的图像。该方法克服了传统平台直方图均衡算法噪声过大及亮度突变的缺点,动态结合了传统的灰度变换增强算法,能根据全图目标与背景灰度的分布情况自适应调整对比度。实验表明,该算法在增强目标对比度的同时有效保留了图像的整体信息,改善了视觉效果。     

基于暗通道先验改进算法的水下图像增强方法研究

针对水下图像受介质散射和吸收的影响所出现的颜色失真、对比度低和细节模糊等问题,提出水下图像增强的暗通道先验改进算法。采用白平衡处理对水下图像的蓝(绿)色偏进行颜色校正,进而在LAB空间对图像L分量进行同态滤波处理,从而获得暗部细节提亮的图像。在RGB空间对图像分别进行CLAHE处理增强图像对比度,解决图像雾化问题,MSRCR处理提高图像色彩饱和度并均衡图像亮度。根据暗通道先验图像计算融合权重系数对所得到的3幅图像进行加权融合与细节增强,得到最终增强图像。实验结果表明,所提算法能够有效消除图像颜色失真情况,增强的图像呈现出高对比度和更清晰的细节。     

基于暗原色先验的夜视图像增强算法

在夜晚条件下拍摄到的图像对比度低,信息缺失,对诸多领域获取图像细节信息造成不便。提出了一种改进的基于暗原色先验的夜视图像增强算法来增强这类图像。采用形态学开运算替换软抠图估计透射率,缩减了算法的时间复杂度。经过暗原色先验增强的图像会放大噪声,为了克服这个缺点,对处理后的图像局部去噪获得保真度更高的图像。实验结果表明,算法可有效增强夜视图像,提高图像对比度、突出细节信息并且减少噪点。     

暗原色先验自适应图像去雾方法

针对传统暗原色先验去雾算法存在的亮区域色彩失真、去雾参 数人工设定等问题,提出了一种基于暗原色先验改进的自适应图像去雾方法。首先,提出快 速OSTU法对雾霾图像亮暗区域进行自适应分割,并分区域获取亮暗区域的暗原色值;其次, 根据亮区域分布情况,对不同区域大气光强进行自适应估计;接着,通过分析雾霾图像直方 图特征,提出采用灰度集中度法自适应计算去雾系数;然后,运用色阶自适应调整方法进行 输出图像的色彩调整;最后,通过开展对比实验,验证了本文算法的优越性。主客观 评价结果表明:本文方法无需人为设定去雾参数,具有较好的 鲁棒性,可适用于多种浓度、 各种场景雾霾图像的去雾处理,获取的图像清晰、色彩自然,对比度高。     

Underwater polarization image restoration based on logarithmic transformation and dark channel

The visibility of the underwater image is reduced due to the backscattering and signal attenuation, especially in highly turbid media. In this paper, we propose a polarization-based underwater image restoration method using logarithmic transformation and dark channel. Logarithmic transformation is first performed while maintaining the degree of polarization of the scene to increase the details of the images. Then we calculate the backscatter value through dark channel to estimate the degree of polarization of backscatter. The restored image can be obtained by the polarimetric recovery method. The experimental results illustrate the capabilities of the proposed method.     

An improved image blind deblurring based on dark channel prior

In order to solve the ringing effect caused by the incorrect estimation of the blur kernel, an improved blind image deblurring algorithm based on the dark channel prior is proposed. First, in the blur kernel estimation stage, high-pass filtering is introduced to enhance the image quality and enhance the edge information to make the blur kernel estimation more accurate. A combination of super Laplacian prior and dark channel prior is introduced to estimate the potential clear image. Then the accurate blur kernel is estimated through alternate iterations from coarse to fine. In the image restoration stage, a weighted least square filter is introduced to suppress the ringing effect of the original clear image to further improve the quality of image restoration. Finally, image deconvolution based on Laplace priors and L₀ regularized priors is used to restore clear images. Experimental results show that our approach improves the peak signal-to-noise ratio(PSNR) by about 0.4 d B and structural similarity(SSIM) by about 0.01, respectively. Compared with the existing image deblurring algorithms, this method can estimate the blur information more accurately, so that the restored image can achieve the effect of keeping the edges and removing ringing.     

基于暗通道先验的红外图像清晰化及FPGA实现

针对红外图像普遍存在目标与背景对比度低、细节模糊等问题,提出一种改进的基于暗通道先验理论的红外图像清晰化算法,并在FPGA平台加以设计实现。该算法通过对输入图像当前像素和邻域的数据进行非线性滤波得到暗通道图像数据,并利用修正函数对透射率进行优化生成透射率查找表。在此基础上,根据暗通道像素值在查找表中查找透射率,并结合大气光散射模型进行图像清晰化处理,从而减少或消除传统暗通道算法产生的块效应及天空等高亮区域的颜色失真。结果表明,处理后的红外图像细节特征丰富、明亮度适宜。所提算法基于FPGA硬件实现仅占用4%的LUT和8%的I/O资源,工作频率最高达188 MHz,远远高于所使用的红外相机工作频率27 MHz,能够满足实时处理视频图像的需求。     

Coordinated underwater dark channel prior for artifact removal of challenging image enhancement

When dehazing underwater images, the patch-by-patch dark channel prior (DCP) method is frequently used. After the DCP-based processing, there are still some drawbacks, such as patch artifacts, and these artifacts will seriously affect the subjective quality of some challenging images. To remove the patch artifacts from the DCP-guided enhancement mechanism, this paper proposes a coordinated underwater dark channel prior (CUDCP) method. The proposed method considers the characteristics of the red-green-blue channels with different attenuation situations, and thus the attenuation ratios of the red-green-blue channels are adaptively coordinated in diverse images. The requirement for color restoration is then assessed by an evaluation criterion, and the color restoration is carried out by using the compensated gray world (CGW) theory, which further coordinates the intensity of various red-green-blue channels. Our method next applies a patch-division average filter in accordance with the sub-patch classification. On the typical dataset, the enhanced images of our CUDCP method have higher average underwater image quality measure (UIQM) scores (about 2.274 8) when compared with the original images and those of some state-of-the-art enhancement methods, while the computational cost of CUDCP (about 88.618 8 s) is slightly higher than that of the original DCP (about 87.493 8 s). The experimental results demonstrate that in comparison to state-of-the-art enhancement methods, the proposed method can significantly reduce patch artifacts in challenging image enhancement, while maintaining the objective quality of such underwater images, and also enhancing their subjective quality at a reasonable computational cost.     

基于颜色衰减先验和视觉显著性的水下图像增强算法

针对水下拍摄的图片存在颜色失真、细节和边缘模 糊等特点,提出了一种基于颜色衰减先验的水下图像增强算法。首先在计算暗通道函数时,用最小值滤波去噪。然后,对图片进行显著图处理,利用颜色先验法则完成深度估计。此滤波方法不仅能降噪,还可以防止颜色失真。最后,基于模型简化获得复原的图片,将其进行伽马变换进行校正,实现柔性去雾。实验结果表明,本文算法与几种典型的水下图像去雾算法相比,能够较好提高图像的清晰度和对比度,同时获得较好的图像颜色。     

结合暗通道先验和MRF理论的单幅图像去雾算法

针对在雾霾环境下获取的图像降质严重、现有算法去雾图结构细节信息丢失较多的问题,提出了一种结合暗通道先验(DCP)和马尔可夫随机场(MRF)的单幅图像去雾算法。该算法先采用子块部分重叠局部直方图均衡(POSHE)对原始雾图进行增强,以提高其对比度,并通过DCP算法获取优化后的透射率;利用MRF模型对图像结构细节信息的约束特性,对透射率进行建模,以进一步细化透射率;由天空域的显著特征,通过分块搜索法求取大气光值。与传统去雾算法相比,该算法能得到更精确的透射率图,有效保持图像结构信息,去雾后的图呈现出丰富的细节和较真实的色彩视觉效果。     

Content-aware dark image enhancement through channel division

The current contrast enhancement algorithms occasionally result in artifacts, overenhancement, and unnatural effects in the processed images. These drawbacks increase for images taken under poor illumination conditions. In this paper, we propose a content-aware algorithm that enhances dark images, sharpens edges, reveals details in textured regions, and preserves the smoothness of flat regions. The algorithm produces an ad hoc transformation for each image, adapting the mapping functions to each image's characteristics to produce the maximum enhancement. We analyze the contrast of the image in the boundary and textured regions, and group the information with common characteristics. These groups model the relations within the image, from which we extract the transformation functions. The results are then adaptively mixed, by considering the human vision system characteristics, to boost the details in the image. Results show that the algorithm can automatically process a wide range of images-e.g., mixed shadow and bright areas, outdoor and indoor lighting, and face images-without introducing artifacts, which is an improvement over many existing methods.