一种电磁干扰源成像多分辨率分区算法北大核心CSCD

在利用抛物反射面对电磁干扰源成像过程中,由于系统衍射受限导致干扰源成像模糊,分辨率低,难以分辨,由于不同频率不同区域干扰源所成图像分辨率不同,具有分区域多分辨率的特征,采用已有超分辨算法难以提高分辨率。利用Mean Shift算法,在原有算法基础上改进使其能够适应多分辨率的电磁干扰源成像,在图像分割的基础上对多分辨率图像进行分块抽离,并采用基于L_R迭代的盲反卷积算法分别对各区域进行分辨率的提高,仿真结果表明算法能够适应对干扰源的多分辨率电磁成像并提高分辨率。     

一种电磁干扰源成像多分辨率分区算法

在利用抛物反射面对电磁干扰源成像过程中,由于系统衍射受限导致干扰源成像模糊,分辨率低,难以分辨,由于不同频率不同区域干扰源所成图像分辨率不同,具有分区域多分辨率的特征,采用已有超分辨算法难以提高分辨率。利用Mean Shift算法,在原有算法基础上改进使其能够适应多分辨率的电磁干扰源成像,在图像分割的基础上对多分辨率图像进行分块抽离,并采用基于L_R迭代的盲反卷积算法分别对各区域进行分辨率的提高,仿真结果表明算法能够适应对干扰源的多分辨率电磁成像并提高分辨率。     

基于维纳滤波的迭代盲解卷积

盲解卷积是在两个卷积因子未知的情况下,通过卷积结果来获知卷积因子的。不考虑噪声,针对高斯模糊图像,在初始估计点扩展函数之后,利用维纳滤波的方法进行频域迭代盲解卷积,达到图像恢复的目的。实验表明,恢复的图像纹理比较清晰,边缘有所改善,主观视觉效果显著。该算法提高了分辨率。     

基于深层残差网络的加速图像超分辨率重建

针对目前卷积神经网络的超分辨率算法存在卷积层数少、模型简单、计算量大、收敛速度慢以及图像纹理模糊等问题,提出了一种基于深层残差网络的加速图像超分辨率重建方法,该方法在提高图像分辨率的同时加快收敛速度。设计更深的卷积神经网络模型来提高精确度,通过残差学习并且使用Adam优化方法使网络模型加速收敛。在原始低分辨率图像上直接进行特征映射,只在网络的末端引入子像素卷积层,将像素进行重新排列,得到高分辨率图像。实验结果表明,在set 5,set 14,BSD100测试集上,所提算法的峰值信噪比与结构相似性指数均高于现有的几种算法,能够恢复更多的图像细节,图像边缘也更加完整且收敛速度更快。     

天文图像多帧盲反卷积收敛性的增强方法

天文图像多帧盲反卷积的收敛性受到初始目标、约束条件和光子噪声等因素的影响.提出了用实际光学成像系统参数确定频率带宽有限约束的方法.用Knox-Thompson 方法重构初始目标相位形成盲反卷积算法的初始目标函数.研究了一种新颖的有效减小光子噪声、边缘效应和振铃现象的方法.根据最大似然估计理论，用期望最大化的优化方法建立了改进的严格约束多帧盲反卷积算法.模拟图像和实际天文图像的复原结果表明，所建立的多帧盲反卷积，可以有效克服大气湍流和减小光子噪声，改善天文观察图像的分辨率，并部分消除光学系统衍射效应对恢复图像的影响. 关键词： 大气光学 天文观测 图像处理和恢复     

变分贝叶斯解卷积法在激光反射层析成像中的应用

基于距离分辨的激光反射层析成像是一种兼顾远距离和高分辨率成像特点的新型激光成像系统。激光发射脉冲宽度大于采样周期时,接收回波被视作反射率分布与发射脉冲的卷积。在重构目标反射率分布轮廓时成像分辨率降低。运用变分贝叶斯方法对1维探测回波信号进行非盲解卷积处理,对探测回波进行脉冲压缩,有效解决了由卷积效应带来的图像降质。设计了激光反射层析实验,并对实测数据进行了处理。重构图像表明此方法有效提高了系统成像分辨率。     

基于模糊度量的激光水下图像复原的盲去卷积方法

由于水体对激光存在着不可克服的吸收和散射效应,距离选通水下激光成像系统所获得的图像存在不同程度的劣化问题,具有信噪比低、边缘模糊等特点.为提高图像质量,将基于模糊度量的盲去卷积方法应用于激光水下成像的图像复原中.结合威尔斯小角度近似得出的点扩展函数与调制传递函数,分别讨论了最大期望,最小均方与多次乘法迭代盲去卷积算法,...     

基于累积量标准差的超分辨光学涨落成像解卷积优化

超分辨光学涨落成像方法通过计算一组随机闪烁图像序列的累积量来提高空间分辨率.在实际实验中,由于计算的图像序列帧数有限,每个像素上累积量估计的误差将显著影响重构图像的均匀性和连续性.传统超分辨光学涨落成像技术由于缺乏对累积量估计的误差分析,在其后续的Lucy-Richardson解卷积算法中,没有对累积量重构图像的噪声添加约束条件.本文利用基于单组有限长数据的累积量标准差公式,计算了超分辨光学涨落显微图像每个像素上的累积量标准差,并将结果引入Lucy-Richardson解卷积算法中作为迭代优化的偏差阈值.模拟和实验结果表明,在相同图像序列长度下,该优化方法显著提高了超分辨重构图像的均匀性和连续性;在同等图像质量下,该方法可缩短图像序列帧数至原来的一半以下,有望用于活细胞动态超分辨成像.     

用神经网络鉴别退化图像的模糊类型

提出了一种用神经网络鉴别退化图像的模糊类型的方法。由于采用不同降质方法得到退化图像的频谱差异较大,以此作为判别依据,用概率神经网络实现了对四种模糊类型:离焦,矩形,运动和高斯模糊的鉴别。根据神经网络的鉴别结果决定点扩散函数的初始估计值,可大大地提高盲解恢复算法的复原质量和系统点扩散函数的估计精度,扩大了算法的实用范围。     

改进的盲解卷积技术在远距离激光光斑图像复原中的应用

为了提高外场实验中远距离测量激光光斑位置的精度,提出利用盲解卷积技术对光斑图像进行事后复原来削弱大气湍流对光斑成像的影响。首先,介绍了经典盲解卷积算法,分析了其不足之处,并提出了一种改进的盲解卷积算法。为了提高目标函数的收敛性和收敛速度,在TV(Total Variation)目标函数加入惩罚项,并对交替迭代法进行改进。然后,用数学方法证明了改进的盲解卷积算法的收敛性。最后,进行了仿真实验。与传统算法相比,用改进算法恢复的图像信噪比至少提升了15%。文中给出了外场试验图像的实际复原效果。     

多局部残差连接注意网络的图像去模糊

针对现有的基于卷积神经网络的图像去模糊算法存在图像纹理细节恢复不清晰的问题,提出了一种基于多局部残差连接注意网络的图像去模糊算法。首先,采用一个卷积层进行浅层特征提取;其次,设计了一种新的基于残差连接和并行注意机制的多局部残差连接注意模块,用于消除图像模糊并提取上下文信息;再次,采用一个基于扩张卷积的成对连接模块进行细节恢复;最后,利用一个卷积层重建清晰图像。实验结果表明：在GoPro数据集上的PSNR (peak signal to noise ratio)和SSIM (structure similarity)分别为31.83 dB、0.927 5,在定性和定量两方面都表明所提方法能够有效地恢复模糊图像的纹理细节,网络性能优于对比方法。     

DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution

This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network. Different from most existing works which rely on the utilization of the coil sensitivities or prior information of predefined transforms, DeepcomplexMRI takes advantage of the availability of a large number of existing multi-channel groudtruth images and uses them as target data to train the deep residual convolutional neural network offline. In particular, a complex convolutional network is proposed to take into account the correlation between the real and imaginary parts of MR images. In addition, the k-space data consistency is further enforced repeatedly in between layers of the network. The evaluations on in vivo datasets show that the proposed method has the capability to recover the desired multi-channel images. Its comparison with state-of-the-art methods also demonstrates that the proposed method can reconstruct the desired MR images more accurately.     

基于PCAU-Net的快速多通道磁共振成像方法

多通道磁共振成像方法采用多个接收线圈同时欠采样k空间以加快成像速度,并基于后处理算法重建图像,但在较高加速因子时,其图像重建质量仍然较差．本文提出了一种基于PCAU-Net的快速多通道磁共振成像方法,将单通道实数U型卷积神经网络拓展到多通道复数卷积神经网络,设计了一种结构不对称的U型网络结构,通过在解码部分减小网络规模以降低模型的复杂度．PCAU-Net网络在跳跃连接前增加了1×1卷积,以实现跨通道信息交互．输入和输出之间利用残差连接为误差的反向传播提供捷径．实验结果表明,使用规则和随机采样模板,在不同加速因子时,相比常规的GRAPPA重建算法和SPIRiT重建方法,本文提出的PCAU-Net方法可高质量重建出磁共振复数图像,并且相比于PCU-Net方法,PCAU-Net减少了模型参数、缩短了训练时间．     

基于多任务卷积神经网络的红外与可见光多分辨率图像融合

红外与可见光图像融合一直是图像领域研究的热点,融合技术能弥补单一传感器的不足,为图像理解与分析提供良好的成像基础。因生产工艺以及成本的限制,红外探测器的分辨率远低于可见光探测器,并在一定程度上因源图像分辨率的差异阻碍了实际应用。针对红外与可见光图像分辨率不一致的问题,提出了用于红外图像超分辨率重建与融合的多任务卷积网络框架,应用于多分辨率图像融合。在网络结构方面,首先设计了双通道网络分别提取红外与可见光特征,使算法不受源图像分辨率的限制;其次提出了特征上采样模块,先用双线性插值方法增加像素个数,再通过多层感知器精细化拟合像素平滑空间与高频空间的映射关系,无需重新训练模型即可实现任意尺度的红外图像上采样;接着将线性注意力引入网络,学习特征空间位置间的非线性关系,抑制无关信息并增强网络对全局信息的表达。在损失函数方面,提出了梯度损失,保留红外与可见光图像中绝对值较大的滤波器响应值,并计算该值与重建的融合图像响应值的Frobenius范数,无需理想的融合图像作为真值监督网络学习就能生成融合图像;此外,在梯度损失、像素损失的共同作用下对多任务模型进行优化,可以同时重建融合图像和高分辨率红外图像...     

Blind motion deblurring using multiple images

Recovery of degraded images due to motion blurring is a challenging problem in digital imaging. Most existing techniques on blind deblurring are not capable of removing complex motion blurring from the blurred images of complex structures. One promising approach is to recover the clear image using multiple images captured for the scene. However, in practice it is observed that such a multi-frame approach can recover a high-quality clear image of the scene only after multiple blurred image frames are accurately aligned during pre-processing, which is a very challenging task even with user interactions. In this paper, by exploring the sparsity of the motion blur kernel and the clear image under certain domains, we propose an alternative iteration approach to simultaneously identify the blur kernels of given blurred images and restore a clear image. Our proposed approach is not only robust to image formation noises, but is also robust to the alignment errors among multiple images. A modified version of linearized Bregman iteration is then developed to efficiently solve the resulting minimization problem. Experiments show that our proposed algorithm is capable of accurately estimating the blur kernels of complex camera motions with minimal requirements on the accuracy of image alignment. As a result, our method is capable of automatically recovering a high-quality clear image from multiple blurred images.     

Image restoration for interlaced scan CCD image with space-variant motion blurs

When the speeds of objects in a scene exceed the temporal resolution of the camera shutter, motion blurs will occur. Since objects are often moving in different directions at different speeds, the degradation of a CCD image is often characterized by space-variant motion blurs. Image restoration algorithms for space-variant motion blurs are available for progressive scan CCD images, but not for interlaced scan images. To address the space-variant image restoration for interlaced scan images, a novel three-step image restoration scheme is proposed. Firstly, one interlaced scan image is divided into odd field and even field images. Secondly, these two field images are further segmented into rectangular blocks and the motion vectors are computed based on these rectangular blocks using an efficient block matching algorithm. Thirdly, image restoration is performed using a blind deconvolution algorithm in the odd or even field image. The final restored image is obtained by combining the restored odd and even field images. The scheme is illustrated by restoring a space-variant blurred moving vehicle image and a synthetic blurred image.     

Dual-Domain Fusion Convolutional Neural Network for Contrast Enhancement Forensics

Contrast enhancement forensics techniques have always been of great interest for the image forensics community, as they can be an effective tool for recovering image history and identifying tampered images. Although several contrast enhancement forensic algorithms have been proposed, their accuracy and robustness against some kinds of processing are still unsatisfactory. In order to attenuate such deficiency, in this paper, we propose a new framework based on dual-domain fusion convolutional neural network to fuse the features of pixel and histogram domains for contrast enhancement forensics. Specifically, we first present a pixel-domain convolutional neural network to automatically capture the patterns of contrast-enhanced images in the pixel domain. Then, we present a histogram-domain convolutional neural network to extract the features in the histogram domain. The feature representations of pixel and histogram domains are fused and fed into two fully connected layers for the classification of contrast-enhanced images. Experimental results show that the proposed method achieves better performance and is robust against pre-JPEG compression and antiforensics attacks, obtaining over 99% detection accuracy for JPEG-compressed images with different QFs and antiforensics attack. In addition, a strategy for performance improvements of CNN-based forensics is explored, which could provide guidance for the design of CNN-based forensics tools.     

辐射成像系统中图像转换屏与物镜耦合的分析

辐射成像系统中,射线沿闪烁体厚度方向产生的光经过镜头形成一个弥散的像。这通常是此类系统空间分辨的主要限制因素。建立了几何光学成像模型,描述了近心光路中此图像的空变特性。用点扩散函数均方根半径表征系统空间分辨性能,给出了图像点扩散函数均方根半径的表达式,其与闪烁体厚度、折射率、镜头相对孔径、成像倍率、射线入射点相对位置直接相关。将硅酸镥晶体3维发光强度分布与镜头进行耦合,分析了闪烁体发光强度分布对耦合的影响。采用点扩散函数均方根半径为最小的原则,建立了一个推导闪烁体相对于物镜放置在最佳位置的方法。     

Multi-frame partially saturated images blind deconvolution

When blurred images have saturated or over-exposed pixels, conventional blind deconvolution approaches often fail to estimate accurate point spread function (PSF) and will introduce local ringing artifacts. In this paper, we propose a method to deal with the problem under the modified multi-frame blind deconvolution framework. First, in the kernel estimation step, a light streak detection scheme using multi-frame blurred images is incorporated into the regularization constraint. Second, we deal with image regions affected by the saturated pixels separately by modeling a weighted matrix during each multi-frame deconvolution iteration process. Both synthetic and real-world examples show that more accurate PSFs can be estimated and restored images have richer details and less negative effects compared to state of art methods.