基于改进CycleGAN的光学图像迁移生成水下小目标合成孔径声纳图像算法研究

针对循环生成对抗网络CycleGAN(Cycle Generative Adversarial Networks)在光学图像迁移生成水下小目标合成孔径声纳图像过程中存在质量差和速度慢的问题,本文提出一种新的特征提取单元SDK(Selective Dilated Kernel),并利用SDK设计了一个新的生成器网络SDKNet.与此同时,提出了一种新的循环一致损失函数MS-CCLF(Multiscale Cyclic Consistent Loss Function),MS-CCLF增加了图像多尺度结构相似性约束.在自建的图像迁移数据集OPT-SAS上,本文SM-CycleGAN(Selective and Multiscale Cycle Generative Adversarial Networks)比原始CycleGAN的图像迁移质量提升4.64％,生成器网络参数降低4.13MB,运算时间减少0.143s.实验结果表明,SM-CycleGAN更适合水下小目标光学图像到合成孔径声纳图像的迁移任务.     

基于生成对抗网络的图像去雾算法

近几年在图像去雾领域中基于深度学习的方法层出不穷,利用循环生成对抗网络(CycleGAN)设计图像去雾算法.在CycleGAN中,通过对生成器进行改进来达到预期的处理效果.在生成器的编码网络和解码网络中选用Leaky ReLU和tanh两种激活函数,并对转换网络的残差块进行减少数量处理和加权优化处理.本设计能够更好地展...     

基于循环生成对抗网络的超分辨率重建算法研究

为了提高图像超分辨率重建的效果,该文将注意力机制引入多级残差网络(Multi-level Residual Attention Network,MRAN)作为CycleGAN的重建网络,提出了基于循环生成对抗网络(CycleGAN)的超分辨率重建模型MRA-GAN.MRA-GAN模型中重建网络负责将低分辨率(LR)图像...     

网络切片场景下基于分布式生成对抗网络的服务功能链异常检测

针对网络切片场景中，由于软硬件异常而导致服务功能链(SFC)异常的问题，该文提出一种基于分布式生成对抗网络(GAN)的时间序列异常检测模型(DTSGAN)。首先，为学习SFC中正常数据的特征，提出分布式GAN架构，对SFC中包含的多个虚拟网络功能(VNF)进行异常检测；其次，针对时间序列数据构建一种基于滑动窗口数据特征提取器，通过提取数据的两种衍生特性和8种统计特征以挖掘深层次特征，得到特征序列；最后，为学习并重构数据特征，提出时间卷积网络(TCN)与自动编码器(AE)构建的3层编解码器作为分布式生成器，生成器通过异常得分函数衡量重构数据与输入数据的差异以检测VNF的状态，进而完成SFC的异常检测。在数据集Clearwater上采用准确率、精确率、召回率和F1分数这4个性能指标验证了该文所提模型的有效性和稳定性。     

一种改进CycleGAN的低照度图像增强网络

为了提高CycleGAN对低照度图像增强后的细节分辨能力,提高图像整体的视觉质量,提出了一种改进CycleGAN的低照度图像增强算法.该网络的生成器由低光照增强模块和亮度均衡处理模块组成,用以学习低照度图像到正常照度图像的特征映射.以多尺度卷积和残差空洞卷积构建基于U-Net的低光照增强模块,提高网络对增强后图像细节信...     

结合强监督学习和生成对抗网络的图像去雾

针对现有去雾算法的复原图像易出现颜色失真与细节丢失问题,提出了一种基于改进循环生成对抗网络(cycle-consistent generative adversarial networks,CycleGAN)的端到端图像去雾方法,并无需依赖于大气散射模型的约束。网络生成器整体采用Encoder-Decoder架构,同时为有效学习有雾图像与清晰图像间的映射关系,在训练优化目标中结合图像自身属性构建了增强的高频损失与特征损失函数,实现对不同数据域的特征鉴别并进一步保证图像纹理结构。此外为约束复原图像与真实清晰图像颜色的一致性,提出了二阶段学习策略。首先通过非配对数据集对改进CycleGAN进行弱监督训练学习,然后于第二阶段利用部分成对数据集以强监督方式训练正向生成网络,在提高去雾网络稳定性的同时,使复原效果更接近于真实清晰图像风格。实验结果表明,所提去雾方法的峰值信噪比(peak signal to noise ratio,PSNR)和结构相似性(structural similarity,SSIM)指标值相比同类CycleGAN算法分别提升了12.43%与5.53%,并且同其他方法在视觉效果与量化指标的对比结果中也验证了其性能的有效性。     

基于空间特征的生成对抗网络数据生成方法

传统的生成对抗网络(GAN)在特征图较大的情况下，忽略了原始特征的表示和结构信息，并且生成图像的像素之间缺乏远距离相关性，从而导致生成的图像质量较低。为了进一步提高生成图像的质量，该文提出一种基于空间特征的生成对抗网络数据生成方法(SF-GAN)。该方法首先将空间金字塔网络加入生成器和判别器，来更好地捕捉图像的边缘等重要的描述信息；然后将生成器和判别器进行特征加强，来建模像素之间的远距离相关性。使用CelebA,SVHN,CIFAR-10等小规模数据集进行实验，通过定性和盗梦空间得分(IS)、弗雷歇距离(FID)定量评估证明了所提方法相比梯度惩罚生成对抗网络(WGAN-GP)、自注意力生成对抗网络(SAGAN)能使生成的图像具有更高的质量。并且通过实验证明了该方法生成的数据能够进一步提升分类模型的训练效果。     

基于相对生成对抗网络的低清小脸幻构

针对当前代表性低清小脸幻构方法存在的视觉真实感弱、网络结构复杂等问题,提出了一种基于相对生成对抗网络的低清小脸幻构方法(tfh-RGAN)。该文方法的网络架构包括幻构生成器和判别器两个部分,通过像素损失函数和相对生成对抗损失函数的联合最小化,实现生成器和判别器的交替迭代训练。其中,幻构生成器结合了残差块、稠密块以及深度可分离卷积算子,保证幻构效果和网络深度的同时降低生成器的参数量;判别器采用图像分类问题中的全卷积网络,通过先后去除批归一化层、添加全连接层,充分挖掘相对生成对抗网络在低清小脸幻构问题上的能力极限。实验结果表明,在不额外显式引入任何人脸结构先验的条件下,该文方法能够以更简练的网络架构输出清晰度更高、真实感更强的幻构人脸。从定量角度看,该文方法的峰值信噪比相较之前的若干代表性方法可提高0.25～1.51 dB。     

基于相对生成对抗网络的低清小脸幻构

针对当前代表性低清小脸幻构方法存在的视觉真实感弱、网络结构复杂等问题,提出了一种基于相对生成对抗网络的低清小脸幻构方法(tfh-RGAN).该文方法的网络架构包括幻构生成器和判别器两个部分,通过像素损失函数和相对生成对抗损失函数的联合最小化,实现生成器和判别器的交替迭代训练.其中,幻构生成器结合了残差块、稠密块以及深度可分离卷积算子,保证幻构效果和网络深度的同时降低生成器的参数量;判别器采用图像分类问题中的全卷积网络,通过先后去除批归一化层、添加全连接层,充分挖掘相对生成对抗网络在低清小脸幻构问题上的能力极限.实验结果表明,在不额外显式引入任何人脸结构先验的条件下,该文方法能够以更简练的网络架构输出清晰度更高、真实感更强的幻构人脸.从定量角度看,该文方法的峰值信噪比相较之前的若干代表性方法可提高0.25～1.51 dB.     

改进DCGAN数据增强的番茄叶子病害图像识别

针对番茄叶子病害图像难以采集的问题，提出一种基于生成对抗网络的番茄叶子病害图像增强方法——Residual Network and Wasserstein Attached Spectral Normalization DCGAN(RWS＿DCGAN)。带有谱归一化的残差网络结构构建了新型的生成器模型和判别器模型，引入带有梯度惩罚项的Wasserstein距离。通过实验表明，改进的生成对抗网络RWS＿DCGAN相较于常规增强方法和DCGAN增强方法，能生成病害明显的番茄叶子病害图像，扩充样本数据集，进而能提升分类网络的识别准确率。     

Single image dehazing using improved cycleGAN

Haze is an aggregation of very fine, widely dispersed, solid and/or liquid particles suspended in the atmosphere. In this paper, we propose an end-to-end network for single image dehazing, which enhances the CycleGAN model by introducing a transformer architecture within the generator, which is specific for haze removal. The proposed model is trained in an unpaired fashion with clear and hazy images altogether and does not require pairs of hazy and corresponding ground-truth clear images. Furthermore, the proposed model does not depend on estimating the parameters of the atmospheric scattering model. Rather, it uses a K-estimation module as the generator’s transformer for complete end-to-end modeling. The feature transformer introduced in the proposed generator model transforms the encoded features into desired feature space and then feeds them into the CycleGAN decoder to create a clear image. In the proposed model we further modified the cycle consistency loss to include the SSIM loss along with pixel-wise mean loss to produce a new loss function specific for the reconstruction task, which enhances the performance of the proposed model. The model performs well even on the high-resolution images provided in the NTIRE 2019 challenge dataset for single image dehazing. Further, we perform experiments on NYU-Depth and reside beta datasets. Results of our experiments show the efficacy of the proposed approach compared to the state-of-the-art in removing the haze from the input image.     

EdgeGAN: One-way mapping generative adversarial network based on the edge information for unpaired training set

Image conversion has attracted mounting attention due to its practical applications. This paper proposes a lightweight network structure that can implement unpaired training sets to complete one-way image mapping, based on the generative adversarial network (GAN) and a fixed-parameter edge detection convolution kernel. Compared with the cycle consistent adversarial network (CycleGAN), the proposed network features simpler structure, fewer parameters (only 37.48% of the parameters in CycleGAN), and less training cost (only 35.47% of the GPU memory usage and 17.67% of the single iteration time in CycleGAN). Remarkably, the cyclic consistency becomes not mandatory for ensuring the consistency of the content before and after image mapping. This network has achieved significant processing effects in some image translation tasks, and its effectiveness and validity have been well demonstrated through typical experiments. In the quantitative classification evaluation based on VGG-16, the algorithm proposed in this paper has achieved superior performance.     

基于DDR CycleGAN的红外图像数据增强

提出了一种基于双鉴别器相对循环一致性生成对抗网络(DDR-CycleGAN)的红外图像数据生成方法。针对双鉴别器监督机制易出现的过度优化造成的性能下降问题,该方法在双鉴别器循环一致性生成对抗网络(DD-CycleGAN)中加入了相对概率的思想,采用鉴别器鉴别图像的相对真实概率替代绝对真实概率,使得生成图片更加接近真实图片。本文方法采用FLIR数据集进行训练和测试,实验结果表明本文方法相比DD-CycleGAN在可见光图像生成红外图像的图像质量上,峰值信噪比提高了3.91%,FID(Frechet Inception Distance score)降低了3.81%。     

Underwater image enhancement based on conditional generative adversarial network

Underwater images play an essential role in acquiring and understanding underwater information. High-quality underwater images can guarantee the reliability of underwater intelligent systems. Unfortunately, underwater images are characterized by low contrast, color casts, blurring, low light, and uneven illumination, which severely affects the perception and processing of underwater information. To improve the quality of acquired underwater images, numerous methods have been proposed, particularly with the emergence of deep learning technologies. However, the performance of underwater image enhancement methods is still unsatisfactory due to lacking sufficient training data and effective network structures. In this paper, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear underwater image is achieved by a multi-scale generator. Besides, we employ a dual discriminator to grab local and global semantic information, which enforces the generated results by the multi-scale generator realistic and natural. Experiments on real-world and synthetic underwater images demonstrate that the proposed method performs favorable against the state-of-the-art underwater image enhancement methods.     

基于改进循环生成式对抗网络的图像风格迁移

图像间的风格迁移是一类将图片在不同领域进行转换的方法。随着生成式对抗网络在深度学习中的快速发展,其在图像风格迁移领域中的应用被日益关注。但经典算法存在配对训练数据较难获取,生成图片效果差的缺点。该文提出一种改进循环生成式对抗网络(CycleGAN++),取消了环形网络,并在图像生成阶段将目标域与源域的先验信息与相应图片进行纵深级联;优化了损失函数,采用分类损失代替循环一致损失,实现了不依赖训练数据映射的图像风格迁移。采用CelebA和Cityscapes数据集进行实验评测,结果表明在亚马逊劳务平台感知研究(AMT perceptual studies)与全卷积网络得分(FCN score)两个经典测试指标中,该文算法比CycleGAN, IcGAN, CoGAN, DIAT等经典算法取得了更高的精度。     

Event-guided low light image enhancement via a dual branch GAN

In the low light conditions, images are corrupted by low contrast and severe noise, but event cameras capture event streams with clear edge structures. Therefore, we propose an Event-Guided Low Light Image Enhancement method using a dual branch generative adversarial networks and recover clear structure with the guide of events. To overcome the lack of paired training datasets, we first synthesize three datasets containing low-light event streams, low-light images, and the ground truth normal-light images. Then, in the generator network, we develop an end-to-end dual branch network consisting of a image enhancement branch and a gradient reconstruction branch. The image enhancement branch is employed to enhance the low light images, and the gradient reconstruction branch is utilized to learn the gradient from events. Moreover, we develops the attention based event-image feature fusion module which selectively fuses the event and low-light image features, and the fused features are concatenated into the image enhancement branch and gradient reconstruction branch, which respectively generate the enhanced images with clear structure and more accurate gradient images. Extensive experiments on synthetic and real datasets demonstrate that the proposed event guided low light image enhancement method produces visually more appealing enhancement images, and achieves a good performance in structure preservation and denoising over state-of-the-arts.     

一种水上目标可见光图像生成红外图像的方法

红外警戒系统、红外成像制导导弹等军事装备在进行性能评估和模拟训练过程中都需要大量红外仿真图像,但目前红外仿真软件普遍存在生成红外仿真图像逼真度差、软件普适性不好等问题,且国外技术封锁造成我国红外仿真软件发展缓慢。因此,针对国内可见光图像仿真技术日趋成熟的现状,为提高红外仿真图像质量,本文提出了一种采用循环生成对抗网络、由可见光图像生成红外仿真图像的方法,并通过实验验证该算法是有效可行的。该算法首先通过区域生长算法从采集的可见光图像中提取水上目标,建立了水上目标可见光图像生成红外图像的训练数据集;然后利用训练好的网络生成红外仿真图像。测试实验表明,采用这种方法所生成的水上目标红外仿真图像视觉效果接近真实红外图像,可实际应用于海军红外军事装备模拟试验和训练系统。     

DCA-CycleGAN: Unsupervised single image dehazing using Dark Channel Attention optimized CycleGAN

Single image dehazing has great significance in computer vision. In this paper, we propose a novel unsupervised Dark Channel Attention optimized CycleGAN (DCA-CycleGAN) to deal with the challenging scene with uneven and dense haze concentration. Firstly, the DCA-CycleGAN adopts the dark channel as input and then generate attention through a DCA subnetwork to handle the nonhomogeneous haze. Secondly, in addition to the conventional global discriminator, we also leverage two local discriminators to enhance the dehazing performance on the local dense haze, and a new local adversarial loss calculated strategy is been proposed. Specifically, the dehazing generator consists of two subnetworks: an auto-encoder and a dark channel attention subnetwork. The auto-encoder consists of an encoder, a feature transformation module, and a decoder. The dark channel attention subnetwork has the same structure as the encoder and the feature transformation module to ensure the same receptive field, which utilizes the dark channel to generate attention map and fine-tune the auto-encoder. Experimental results against several state-of-the-art methods demonstrate that our method can generate better visual effects, and is effective.     

医学图像增强系统设计

为了改善医学图像的视觉效果,提高图像的清晰度,使之更适合于机器的分析处理以及人的视觉特性,并突出病灶点,为病理学诊断和临床诊断提供可靠依据。设计了一个对医学图像十分具有针对性的图像增强系统。针对CT图像的电子噪声提出了基于修正维纳滤波的小波包去噪算法;针对B型超声图像的散斑噪声提出了基于脉冲耦合神经网络(PCNN)模型的小波自适应斑点噪声滤除算法;针对医学图像对比度低,边缘信息模糊等特点,提出了基于小波变换的医学图像增强算法。当噪声方差为0.01时,基于脉冲耦合神经网络(PCNN)模型的小波自适应斑点噪声滤除算法获得的PSNR比经Wiener滤波方法获得的PSNR高出9 dB。系统能快速找到噪声点进行定点去噪,能有效提高医学图像的对比度,增强边缘细节信息,突出病灶点的位置,从而达到较好的处理效果,为医疗工作者观察病症提供更加清晰准确的依据。