基于无监督学习的低照度图像增强算法

针对目前低照度图像增强算法存在恢复细节丢失、网络复杂度高和配对数据集获取难度大等问题,提出了一种基于无监督学习的图像增强算法。在YIQ色彩空间中,通过构建的轻量化网络和幂指函数计算亮度通道Y的增强曲线,从而获得曝光较差区域增强和高光区域遏制的图像。该网络使用的无参考损失函数可以隐式地评估图像增强质量并驱动网络学习。实验对比结果表明,该算法在可训练参数和模型权重仅占9.5 k/88 kB的情形下,在视觉效果与图像质量指标上都取得了具有竞争力的结果。     

基于深度学习的低照度图像增强方法

在低照度环境下采集的图像往往亮度不足,导致在后续视觉任务中难以有效利用.针对这一问题,过去的低照度图像增强方法大多在极度低光场景中表现失败,甚至放大了图像中的底层噪声.为了解决这一难题,本文提出了 一种新的基于深度学习的端到端神经网络,该网络主要通过空间和通道双重注意力机制来抑制色差和噪声,其中空间注意力模块利用图像的...     

Low-light image enhancement network based on multi-stream information supplement

Images captured under low-light conditions often suffer from severe loss of structural details and color; therefore, image-enhancement algorithms are widely used in low-light image restoration. Image-enhancement algorithms based on the traditional Retinex model only consider the change in the image brightness, while ignoring the noise and color deviation generated during the process of image restoration. In view of these problems, this paper proposes an image enhancement network based on multi-stream information supplement, which contains a mainstream structure and two branch structures with different scales. To obtain richer feature information, an information complementary module is designed to realize the information supplement for the three structures. The feature information from the three structures is then concatenated to perform the final image recovery operation. To restore more abundant structures and realistic colors, we define a joint loss function by combining the L1 loss, structural similarity loss, and color-difference loss to guide the network training. The experimental results show that the proposed network achieves satisfactory performance in both subjective and objective aspects.

     

Low-light image enhancement based on Retinex theory and dual-tree complex wavelet transform

In order to enhance the contrast of low-light images and reduce noise in them, we propose an image enhancement method based on Retinex theory and dual-tree complex wavelet transform (DT-CWT). The method first converts an image from the RGB color space to the HSV color space and decomposes the V-channel by dual-tree complex wavelet transform. Next, an improved local adaptive tone mapping method is applied to process the low frequency components of the image, and a soft threshold denoising algorithm is used to denoise the high frequency components of the image. Then, the V-channel is rebuilt and the contrast is adjusted using white balance method. Finally, the processed image is converted back into the RGB color space as the enhanced result. Experimental results show that the proposed method can effectively improve the performance in terms of contrast enhancement, noise reduction and color reproduction.     

基于在线估计的视觉SLAM低光照图像增强算法

为了提升基于特征点的双目视觉定位算法在低光照环境下定位的准确性,提出一种基于在线估计的视觉同步定位与地图构建(simultaneous localization and mapping,SLAM)低光照图像增强算法.通过在线估计图像亮度值,实时更新图像增强算法的参数,解决了基于固定参数的图像增强算法在图像较亮、较暗等情...     

基于NSST和CLAHE的零件表面缺陷图像增强算法研究

为了改善传统剪切波变换在零件表面缺陷图像中边缘不明显和去除噪声效果不理想的问题,本文提出了基于非下采样剪切波变换(NSST)和限制对比度的自适应直方图均衡化(CLAHE)的图像增强算法,在后续的Canny算子边缘检测中效果较好.首先,将缺陷图像进行NSST变换,获得相应的高频图像和低频图像;其次,将高频图像进行CLAHE变换,NSST逆变换的图像经过Canny算子应用于检测缺陷图像边缘.结果表明:该算法在面对零件的拉伤、倒偏角和碰伤缺陷时,均获得了较高的峰值信噪比和信息熵;在增强边缘的同时,能够更好的去除噪声,证明了其有效性和鲁棒性.     

一种基于FPGA的彩色图像实时增强方法

彩色图像中包含了丰富的颜色信息,能够直观地感知世界,它使我们的工作生活更加便利。但是,由于一些恶劣环境的影响,彩色图像的成像会出现模糊、目标被淹没、对比度偏低等问题。针对此问题,本文设计了一款基于FPGA的嵌入式实时图像增强处理系统。并提出一种灰度值拉伸变换方法,将该方法直接对RGB色彩空间的R、G、B三分量进行增强处理,既增大了灰度值的变化范围提高人眼视觉效果,也避免了色彩空间转换带来的计算量及节省了处理时间满足了工程的实时性要求。目前该系统已在实际工程项目中应用,工程结果表明该系统工作稳定有效,能够有效解决工程中出现的光线条件差,低对比度情况下的彩色图像增强问题。     

基于NSST和人眼感知保真约束的图像自适应增强

鉴于现有的图像增强方法在提高图像对比度、清 晰度等方面仍存在不足,提出了基于非下采样剪切波变换 (NSST,non-subsampled shearlet transform)和人眼感知保真约束的自适应 增强方法。首先对输 入图像进行NSST,分解为一个低频子带图像和多个高频子带图像;然后利用非线性增益 函数增强高 频子带系数,同时对低频部分进行分块局部增强;考虑到传统分块局部增强存在局部图像块 间不连续进而 导致失真的情况,引入了人眼感知保真约束条件,并将其转化为求解一个典型的线性优化问 题,由此获取 增强参数,实现低频部分的增强;最后融合处理后的高低频子带系数,重构出期望的增强 图像。大量实验 结果表明,与近年提出的4种同类方法相比,本文方法所得增强图像的主观视觉效果更好 ,在清晰度、 局部对比度以及全局对比度等定量评价指标上平均高出50%,且实时性良好。     

Low-light image enhancement by diffusion pyramid with residuals

With the advancement of the camera-related technology in mobile devices, the vast amount of photos have been taken and shared in our daily life. However, many users still have unsatisfactory experiences with low-visible photos, which are frequently acquired under complicated real-world environments. In this paper, a novel yet simple method for low-light image enhancement has been proposed without any learning procedure. The key idea of the proposed method is to estimate properties of the scene illumination both in global and local manner by exploiting the diffusion pyramid with residuals. Specifically, the residual of each scale level in the diffusion pyramid is combined with the corresponding input. This restored result efficiently highlights local details across different scale spaces, thus it is helpful for preserving the boundary of illuminations. By conducting max-pooling with restored results from different levels of the diffusion pyramid, which are resized to the original resolution, the illumination component is accurately inferred from a given image. Compared to recent learning-based approaches, one important advantage of the proposed method is to effectively avoid the overfitting problem to the specific training dataset. Experimental results on various benchmark datasets demonstrate the efficiency and robustness of the proposed method for low-light image enhancement in real-world scenarios.     

基于视觉感受野的夜间彩色图像自适应增强算法

针对夜间环境造成的图像对比度下降和增强过程中带来的噪声、过曝和光晕效应等问题,提出了一种基于视觉感受野的夜间彩色图像自适应增强算法。首先将图像转换到HSV空间,鉴于视觉感知的对比度敏感特性,利用中心兴奋区及外周抑制区组成的拮抗式同心圆双高斯差(DOG)感受野模型对图像亮度空间V进行对比度自适应调节,并对模型参数σ1、σ2和局部对比度都进行量化水平为4的均匀量化,局部对比度较高的量化区间采用较小模型参数,局部对比度较低的量化区间采用较大的模型参数,模型参数A2与局部对比度成反比进行微调,最后将图像转换到回RGB空间。通过与流行算法MSRCR、NPE及LIME的对比实验表明,该算法获得了较好的主观视觉效果,且在对比度、亮度提高的同时避免了暗区域噪声过大,并更好地增强了轮廓信息。     

基于视觉特性的非线性多尺度彩色图像增强

[目的]针对图像在低光照下的亮度和对比度偏低的问题,提出一种基于视觉特性的非线性多尺度彩色图像增强算法.[方法]该算法将彩色图像从RGB色彩空间转化到HSI色彩空间,保持H分量不变,对S分量进行指数拉伸,对Ⅰ分量利用视觉系统模型和非线性映射方法实现图像对比度增强,再通过自适应的亮度调整增加图像的全局亮度.最后将HSI色彩空间转化到RGB色彩空间,从而实现对彩色图像自适应增强.[结果]通过对低光照彩色图像进行增强测试,其测试结果表明,[结论]该算法能够自适应地调整图像的全局亮度,增加图像的局部细节对比度,并保持其原色彩,提升彩色图像在低光照下的视见度.     

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。     

Low-light image enhancement via deep Retinex decomposition and bilateral learning

Low-light images enhancement is a challenging task because enhancing image brightness and reducing image degradation should be considered simultaneously. Although existing deep learning-based methods improve the visibility of low-light images, many of them tend to lose details or sacrifice naturalness. To address these issues, we present a multi-stage network for low-light image enhancement, which consists of three sub-networks. More specifically, inspired by the Retinex theory and the bilateral grid technique, we first design a reflectance and illumination decomposition network to decompose an image into reflectance and illumination maps efficiently. To increase the brightness while preserving edge information, we then devise an attention-guided illumination adjustment network. The reflectance and the adjusted illumination maps are fused and refined by adversarial learning to reduce image degradation and improve image naturalness. Experiments are conducted on our rebuilt SICE low-light image dataset, which consists of 1380 real paired images and a public dataset LOL, which has 500 real paired images and 1000 synthetic paired images. Experimental results show that the proposed method outperforms state-of-the-art methods quantitatively and qualitatively.     

基于NSST和改进PCNN的医学图像融合

为了解决单一模态医学图像的局限性,提出了一种 基于非下采样剪切波变换(NSST)和改进型脉冲耦合神经网络(PCNN)相结合的多模态医学图 像融合方法。首先,利用NSST对源图像进行多尺度、多方向分解,得到 低频子带系数和高频子带系数;其 次,低频子带系数由区域能量和方差求取区域特征,采用基于区域特征加权的方式进行融合 ;高频内层子 带系数先通过PCNN求出区域点火特性,再与平均梯度加权的方式进行选择,高频外层子 带系数采用区 域绝对值取大的融合规则;最后,通过逆NSST重构图像。实验结果表明:与常用融合 规则对比,在 主观效果上,本文的融合图像可以保留源图像的边缘信息,得到更好的视觉效果;在客观指 标上,本文方法 融合得到的图像在互信息(MI)、边缘评价因子(QAB/F)和 结构相似度(SSIM)等客观评价指标上取得更好的效果。     

Low-light image enhancement algorithm using a residual network with semantic information

Aiming to solve the poor performance of low illumination enhancement algorithms on uneven illumination images, a low-light image enhancement(LIME) algorithm based on a residual network was proposed. The algorithm constructs a deep network that uses residual modules to extract image feature information and semantic modules to extract image semantic information from different levels. Moreover, a composite loss function was also designed for the process of low illumination image enhancement, which ...     

彩色图像的FPGA实时增强系统实现

为了对彩色图像进行实时增强,本文提出了采用基于插值的分段拉伸算法。首先将彩色RGB图像转换为HSV空间,在该空间,对图像直方图进行基于差值的分段拉伸处理,以达到对图像增强的目的。经过该方法增强后的图像,细节信息更加丰富,图像的清晰度得到了改善,图像的视觉质量也得到了明显提高。经过该算法增强后图像的灰度平均梯度值为直方图均衡化算法的1.95倍。应用现场可编程门阵列(FPGA)为中央处理器,通过并行处理结构及流水线技术,完成图像空间的转换和图像的实时增强算法,简化了系统设计,使处理系统硬件更加紧凑,运行更加可靠。给出了系统主要功能模块的实现方法,经现场调试,可完成每秒30帧×1 024×1 024×24bit数据的处理,与直方图均衡化等传统图像增强算法相比,该算法计算时间缩短了0.807ms。该系统具有集成度高、图像处理速度快和实时性强等特点。     

R2RNet: Low-light image enhancement via Real-low to Real-normal Network

Images captured in weak illumination conditions could seriously degrade the image quality. Solving a series of degradation of low-light images can effectively improve the visual quality of images and the performance of high-level visual tasks. In this study, a novel Retinex-based Real-low to Real-normal Network (R2RNet) is proposed for low-light image enhancement, which includes three subnets: a Decom-Net, a Denoise-Net, and a Relight-Net. These three subnets are used for decomposing, denoising, contrast enhancement and detail preservation, respectively. Our R2RNet not only uses the spatial information of the image to improve the contrast but also uses the frequency information to preserve the details. Therefore, our model achieved more robust results for all degraded images. Unlike most previous methods that were trained on synthetic images, we collected the first Large-Scale Real-World paired low/normal-light images dataset (LSRW dataset) to satisfy the training requirements and make our model have better generalization performance in real-world scenes. Extensive experiments on publicly available datasets demonstrated that our method outperforms the existing state-of-the-art methods both quantitatively and visually. In addition, our results showed that the performance of the high-level visual task (i.e., face detection) can be effectively improved by using the enhanced results obtained by our method in low-light conditions. Our codes and the LSRW dataset are available at: https://github.com/JianghaiSCU/R2RNet.     

基于NSST和高斯混合模型的医学图像融合算法

提出了一种基于非下采样剪切波变换（Non-subsampled shearlet transform, NSST）和高斯混合模型的医学彩色图像融合算法。首先将彩色图像转换到HSI颜色空间,提取其色度分量图像、饱和度分量图像和强度分量图像;然后对强度分量图像和MRI图像进行NSST变换,其中低频系数采用基于区域系数改进拉普拉斯能量和（Sum-modified-Laplacian,SML）加权的融合规则,高频系数采用高斯混合模型估计参数取大的融合规则;对融合后的系数进行NSST逆变换重构融合后的强度分量图像;最后将融合后的强度分量图像与色度分量图像、饱和度分量图像混合得到融合后的HSI图像,再将HSI图像转换到RGB颜色空间得到融合后的彩色图像。仿真实验表明,该算法在视觉效果和客观评价指标上具有更好的融合效果。     

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。     

基于颜色传递和目标增强的夜视图像彩色融合

颜色传递是获得夜视图像自然彩色的一种方法,以红外和微光图像为研究对象,提出了一种基于颜色传递和目标增强的夜视图像彩色融合方法。首先结合红外和微光图像各自的特点,采用TNO法生成伪彩色融合图像(目标图像),很好地保留了图像的细节信息,然后选取一幅相近的参考图像,把目标图像和参考图像转换到YCbCr颜色空间进行各个通道一阶(均值)和二阶(标准差)统计量匹配的颜色传递,同时在Cr通道引入一个对比度增强因子来增强图像中的兴趣目标。实验结果表明,文中方法不仅使得夜视图像获得了如白天参考图像般自然、真实的色彩,而且提高了图像的细节,目标也更加突出,更有利于观察者对场景的理解。