Learning deep transmission network for efficient image dehazing

Multimedia Tools and Applications - Single image dehazing algorithms are recently attracting more and more attention from many researchers because of their flexibility and practicality. However,...     

Adaptive dehazing control factor based fast single image dehazing

The single image dehazing is performed using atmospheric scattering model (ASM). The ASM is based on transmission and atmospheric light. Thus, accurate estimation of transmission is essential for quality single image dehazing. Single image dehazing is of prime focus in research nowadays. The proposed work presents a fast and accurate method for single image dehazing. The proposed method works in two folds; (i) An adaptive dehazing control factor is proposed to estimate accurate transmission, which is based on difference of maximum and minimum color channel of hazy image, and (ii) a mathematical model to compute probability of a pixel to be at short distance is presented, which is utilized to locate haziest region of the image to compute the value of atmospheric light. The proposed method obtains visually compelling results, and recovers the information content (such as structural similarity, color, and visibility) accurately. The computation speed and accuracy of the proposed method is proved using quantitative and qualitative comparison of results with state of the art dehazing methods.

     

正交频分复用系统中基于人眼视觉系统的自适应图像传输

针对传统的图像传输方法,提出了一种基于人眼视觉系统的自适应图像传输方案。在OFDM系统中,通过将自适应技术与信源分割及信道特性相结合的方法,实现在频率选择性慢衰落信道中高质量的图像传输。为验证该方法的良好性能,三种不同图像源被用于仿真程序中。仿真结果及理论分析可以证明,自适应图像传输与传统的图像传输相比,可大幅地提高接收图像的峰值信噪比。     

Bounding function for fast computation of transmission in single image dehazing

Multimedia Tools and Applications - There exist multiple dehazed images corresponding to a single hazy image due to ill-posed nature of single image dehazing (SID), making it a challenging problem....     

Joint dehazing and denoising for single nighttime image via multi-scale decomposition

Outdoor images taken in the foggy or haze weather conditions are usually contaminated due to the presence of turbid medium in the atmosphere. Moreover, images captured under nighttime haze scenarios will be degraded even further owing to some unexpected factors. However, most existing dehazing methods mainly focus on daytime haze scenes, which cannot effectively remove the haze and suppress the noise for nighttime hazy images. To overcome these intractable problems, a joint dehazing and denoising framework for nighttime haze scenes is proposed based on multi-scale decomposition. First, the glow is removed by using its characteristic of the relative smoothness and the gamma correction operation is employed on the glow-free image for improving the overall brightness. Then, we adopt the multi-scale strategy to decompose the nighttime hazy image into a structure layer and multiple texture layers based on the total variation. Subsequently, the structure layer is dehazed based on the dark channel prior (DCP) and the texture layers are denoised based on color block-matching 3D filtering (CBM3D) prior to enhancement. Finally, the dehazed structure layer and the enhanced texture layers are fused into a dehazing result. Experiments on real-world and synthetic nighttime hazy images reveal that the proposed nighttime dehazing framework outperforms other state-of-the-art daytime and nighttime dehazing techniques.

     

Adaptive image camouflage using human visual system model

Multimedia Tools and Applications - The development of image decryption techniques means that some current encryption techniques that turn a secret image into a meaningless image are no longer...     

Local albedo-insensitive single image dehazing

In this paper, we present a new algorithm to remove haze from a single image. The proposed algorithm extracts transmission iteratively under the assumption that large-scale chromaticity variations are due to transmission while small-scale luminance variations are due to scene albedo. A nonlinear edge-preserving filter is introduced to incrementally refine subtle transmission map while still keeping sharp transmission map distinct. The algorithm is verified by both synthetic images and real-scene photographs. The results demonstrate that our method can produce transmission maps without being affected by the local albedo variations and, furthermore, recover haze-free images. On top of haze removal, several applications of the transmission map including refocusing and relighting are also implemented.     

基于人类视觉特性的自适应水印嵌入方案*

针对已有算法在嵌入量和嵌入强度自适应控制方面存在的问题,结合人类视觉对纹理区域的感知特性,通过噪声可见函数（NVF）对图像块复杂度的计算,提出了一种在DCT直流系数进行嵌入的水印算法。该算法能够根据图像块复杂度计算结果实现嵌入强度的自适应控制。实验结果表明,所提算法相比已有算法提高了嵌入容量和嵌入强度的自适应控制程度,并且一定程度上避免了由于DC系数嵌入数据所出现的块效应现象,对图像处理和常见的图像攻击也具有很好的稳健性。     

DCNet: dual-cascade network for single image dehazing

Neural Computing and Applications - Image dehazing is a challenging ill-posed problem in the field of computer vision. Existing learning-methods usually use a single convolutional neural network...     

全局平滑和边缘保持的单幅图像去雾

针对现有基于暗原色先验理论的去雾方法在天空区域容易产生失真和边缘定位不准确的问题,提出了一种雾天图像直接去雾方法。根据雾天成像模型和空间变化图像复原思想,构建了数据项;通过深入分析天空区域产生失真的原因、透射率图像和复原图像的边缘特征,构建了约束项,并通过线性组合数据项和约束项,构建了一个能量泛函;利用分步梯度下降流法最优化该能量泛函,实现了复原图像的精确求解。实验结果表明,与传统方法相比,该方法不但能更好地抑制天空区域失真现象的产生,也能更精确地定位复原图像的边缘。     

Correction to: Adaptive image camouflage using human visual system model

Multimedia Tools and Applications - The expression J’ in pages 4, 6, 9, 12 and 13 of the original publication were incorrectly written as J where the symbol prime (‘) was missing. Also...     

基于图像融合的快速单幅图像去雾算法

针对单幅雾霾图像中存在大面积明亮区域,暗通道先验失效、引导滤波算法去雾不彻底和时间复杂度较高的问题,提出了一种基于图像融合的快速单幅图像去雾算法.在大气散射模型的基础上,对大气光值进行区间估计;由暗通道先验法得到透射率的简单估计,由Retinex理论进行多尺度高斯卷积得到透射率的模糊估计,利用图像融合将两者进行像素级融合,得到透射率的精确估计;采用交叉双边滤波进行平滑处理并针对明亮区域修正透射率;对复原图像进行色调调整后得到最终图像.实验表明:算法不仅取得良好的去雾效果和较好的图像色彩,还有效降低了时间复杂度.     

导向滤波优化的单幅去雾算法

针对暗原色先验的单幅去雾算法计算复杂度高,无法满足交通监控系统中实时性需求,且大气光易受白色物体影响,以及天空区域易失真的缺陷和景物边界出现白边现象,提出了基于暗原色改进的快速去雾算法.采用四叉树搜索的算法对大气光进行精确估计,利用最大值滤波后的差值图像估计出天空区域,对透射率进行补偿,利用导向滤波器改进透射率并结合大气散射模型恢复无雾图像.实验结果表明:改进算法改善了原算法去雾效果的同时也提高了算法的速度.     

曝光融合在单幅图像去雾中的应用

针对雾天拍摄图像的降质现象,提出一种简单、有效的单幅图像去雾算法。首先利用暗原色先验知识估计出大气光亮度;然后根据雾天图像的成像物理模型,对每一像素的景深进行较高精度的亚采样,生成对应的虚拟无雾图像备选序列;最后,根据曝光融合算法提出的像素曝光评价指标,利用多分辨率形式的图像融合方法从备选序列中提取出清晰的无雾图像。实验结果表明,该算法既保证了复原图像清晰度,又具有较好的实时性。     

Color and sharpness assessment of single image dehazing

Multimedia Tools and Applications - Image dehazing is the process of enhancing a color image of a natural scene that contains an undesirable veil of fog for visualization or as a pre-processing...     

基于色彩空间单一图像像素级去雾算法

基于雾会降低图像对比度以及边界模糊的实际情况,提出一种基于颜色空间的单幅图像去雾算法。首先计算每个像素在RGB颜色空间中距离灰阶线(原点与点(255,255,255)所确定的直线)的距离,确定深度图像;然后根据灰阶线距离计算每个像素在颜色空间中的新位置,进而获得去雾后的图像。算法具有良好的实用性和并行计算可行性。实验结果表明:算法显著增强了图像的对比度、颜色饱和度等,具有良好的去雾效果。     

一种纸币识别系统的设计

介绍了一种纸币识别系统的硬件设计和对应的识别方法。在硬件设计上,将高速数字信号处理（DSP）技术与复杂可编程逻辑器件（CPLD）和线阵型图像传感器（CCD）相结合;在识别方法上,应用图像处理技术与改进的SOFM神经网络方法识别纸币。实验证明,此系统达到了高速、实时、识别率高的要求。     

结合天空区域识别的单幅图像去雾方法

针对现有图像去雾方法易于在天空区域引入负面视觉效果的缺陷,提出一个结合天空区域识别的单幅图像去雾方法;提出一个新的天空区域特征先验知识,并利用所提先验将雾天降质图像分割为天空与非天空区域;基于天空区域对大气光进行估计,并利用暗通道先验和导向全变分模型对非天空区域的透射率进行估计,从而基于大气散射模型获得去雾处理后的图像;使用一种邻域自适应的Retinex方法克服了去雾处理后图像偏暗的问题。对比实验证明,所提方法相比现有的类似方法具备更好的有效性及鲁棒性。     

Single image dehazing based on single pixel energy minimization

Multimedia Tools and Applications - The common dehazing algorithms always assume that the transmission values of all the pixels in an image block are the same (local consistency assumption)....     

MFID-Net: Multi-scaled feature-fused image dehazing via dynamic weights

Methods based on convolutional neural networks have achieved excellent performance in the image dehazing task. Unfortunately, most of the dehazing methods that exist suffer from loss of detail in the convolution and activation operations and failure to consider the effects of superimposing different intensities of haze, such as under-exposed and over-exposed images. To address these issues, we propose a dynamic dehazing convolution (DDC) based on attentional weight calculation and dynamic weight fusion and a dynamic dehazing activation (DDA) based on the input global context encoding function to address the problem of detail loss. And we propose a multi-scaled feature-fused image dehazing network (MFID-Net) based on DDC and DDA to address the effects of haze superposition. We also design a loss function based on the physical model with dynamic weights. Extensive experimental results demonstrate that the proposed MFID-Net performs favorably against the state-of-the-art algorithms on the hazy dataset while improving further on hazy images with large differences in haze concentration, and producing satisfactory dehazing results. The code is available at https://github.com/awhitewhale/MFID-Net.