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。     

A Robust Point Spread Function Estimation for Out-of-Focus Blurred and Noisy Images Based on a Distribution of Gradient Vectors on the Polar Plane

The estimation of the point spread function (PSF) is a very important and indispensable task for practical image restoration. Various PSF estimation algorithms have been developed, especially for the out-of-focus blur. However, a majority of them are useless in an extremely noisy environment. This paper describes a new robust PSF estimation algorithm based on a distribution of gradient vectors on the logarithmic amplitude spectrum mapped to the polar plane. The proposed algorithm can estimate the out-of-focus PSF accurately and robustly, even for an image highly corrupted by noise. The effectiveness of the proposed algorithm is verified by applying it to the PSF estimation for out-of-focus blurred and noisy images.     

Single frame blind image deconvolution by non-negative sparse matrix factorization

Novel approach to single frame multichannel blind image deconvolution has been formulated recently as non-negative matrix factorization problem with sparseness constraints imposed on the unknown mixing vector that accounts for the case of non-sparse source image. Unlike most of the blind image deconvolution algorithms, the novel approach assumed no a priori knowledge about the blurring kernel and original image. Our contributions in this paper are: (i) we have formulated generalized non-negative matrix factorization approach to blind image deconvolution with sparseness constraints imposed on either unknown mixing vector or unknown source image; (ii) the criteria are established to distinguish whether unknown source image was sparse or not as well as to estimate appropriate sparseness constraint from degraded image itself, thus making the proposed approach completely unsupervised; (iii) an extensive experimental performance evaluation of the non-negative matrix factorization algorithm is presented on the images degraded by the blur caused by the photon sieve, out-of-focus blur with sparse and non-sparse images and blur caused by atmospheric turbulence. The algorithm is compared with the state-of-the-art single frame blind image deconvolution algorithms such as blind Richardson-Lucy algorithm and single frame multichannel independent component analysis based algorithm and non-blind image restoration algorithms such as multiplicative algebraic restoration technique and Van-Cittert algorithms. It has been experimentally demonstrated that proposed algorithm outperforms mentioned non-blind and blind image deconvolution methods.     

去散焦模糊的折反射全向成像系统设计

随着高分辨率传感器和大光圈的采用,光圈和反射面曲率造成的折反射全向成像散焦模糊问题越发突出。提出了一种有效去除散焦模糊的折反射全向成像系统设计。理论分析折反射成像散焦模糊的原因,建立全向图点扩展函数与实景空间物点及成像系统虚像位置的关系;在一次曝光成像时间内匀速旋转镜头对焦环,通过累积曝光使全向图散焦模糊核具有期望的空间不变性;利用反卷积算法对散焦模糊全向图进行复原,得到全局清晰的全向图像。该方法较好地解决了折反射全向成像散焦模糊问题,对提高折反射全向成像质量,促进其在相关领域的广泛应用具有重要意义。     

单幅模糊图像点扩散函数估计的梯度倒谱分析方法研究

针对单幅图像复原算法引入先验信息导致复杂度高、运算效率低的问题, 提出了单幅模糊图像点扩散函数估计的梯度倒谱分析方法. 首先给出了单幅模糊图像梯度倒谱估计其点扩散函数的基本原理, 利用相位恢复策略复原了二维点扩散函数相位信息, 实现了点扩散函数的快速估计; 其次, 为鉴别点扩散函数估计精度, 建立了图像梯度保真约束的全变分正则化图像复原模型, 并采用快速稳定收敛的交替方向策略优化能量函数; 通过对仿真和实拍单幅模糊图像进行的测试实验结果表明, 该方法快速准确地估计出点扩散函数, 克服了传统复原算法收敛速度慢的缺点, 有效抑制了振铃效应、保护了边缘信息, 为大尺寸单幅图像复原的工程化实现提供了理论和技术基础. 关键词： 图像复原 点扩散函数 梯度倒谱分析 全变分     

空间变化PSF非盲去卷积图像复原法综述

传统的图像复原一般认为点扩散函数(PSF)是空间不变的,实际光学系统由于受到像差等因素的影响,并非严格的线性空间不变系统,基于空间变化PSF的非盲去卷积图像复原法逐渐体现其优越性。空间变化PSF的非盲去卷积图像复原法先准确估计图像空间变化的PSF,再利用非盲去卷积算法对图像进行复原,有利于恢复出高质量图像。本文从算法的角度综述了近几年提出的基于空间变化PSF的非盲去卷积图像复原方法,并对比了基于强边缘预测估计PSF的非盲去卷积法、基于模糊噪声图像对PSF估计非盲去卷积法等算法的优缺点,各算法分别在PSF估计精确度、振铃效应抑制效果、适用范围等方面体现出各自的优劣。空间变化PSF的非盲去卷积图像复原法的研究,有利于推进图像复原技术向更高水平发展,使光学系统往轻小型化方向发展,从而在多个科学领域发挥其重要作用。     

基于结构字典学习的图像复原方法

本文提出一种新的结构字典学习方法,并利用它进行图像复原。首先给出结构字典学习的基本内容和方法,然后将傅里叶正则化方法和结构字典学习方法有效整合到图像复原算法中。结构字典学习方法是先将原图像进行结构分解,再分别学习出每个结构图像中的字典,最后利用这些字典对原图像进行稀疏的表示。结合傅里叶正则化,提出了一种有效的迭代图像复原算法:第一步在傅里叶域利用正则化反卷积方法得到图像的初步估计;第二步采用结构字典学习的方法对遗留的噪声进行去噪处理。实验结果表明,提出的方法在改进信噪比和视觉质量上都要优于6种先进的图像复原方法,改进的信噪比平均提升0.5 d B以上。     

Motion deblurring using edge map with blurred/noisy image pairs

Motion deblurring methods using blurred/noisy image pairs usually include denoising process of the noisy image. Because both remaining noise and distorted fine details in the denoised image cause an error on deblurring, we propose an algorithm using an edge map of the noisy image to retain sharp edge information while neglecting noise in any smooth region that does not contain information about the motion that occurred during the exposure. In addition, the blur kernel is efficiently estimated by employing the fast total variation regularization method for the gradients of blurred and noisy images only on edge regions. For latent image restoration, another fidelity term is added, which compares the gradients of the noisy and estimated latent images on edge regions to preserve the fine details of the noisy image. To model a sparse distribution of real-world image gradients, a deconvolution method imposing hyper-Laplacian priors based on an alternating minimization scheme is also derived to restore a latent image efficiently. Experimental results show that the peak signal-to-noise ratios of the restored images against the original latent images have been increased by 11.1% on average, when compared to the existing algorithms using an image pair.     

Blur identification and restoration of degraded images using generalized cross-validation criterion

In this paper, we describe blur identification and restoration of noisy degraded images. The point-spread function (PSF) can be characterized by the quantity of blur. Thus the blur identification problem can be solved as a parameter estimation problem. The estimation method is a generalized cross-validation (GCV) criterion that is known as a powerful measure that can be used to choose the optimal regularization parameter without a priori knowledge about noise. We use the iterative damped-1east squares (DLS) algorithm which is based on the principle of damped least-squares for restoring noisy degraded images.     

A novel modified cepstral based technique for blind estimation of motion blur

In the problem of blind image deconvolution, estimation of blurring kernel is the first and foremost important step. Quality of restored image highly depends upon the accuracy of this estimation. In this paper we propose a modified cepstrum domain approach combined with bit-plane slicing method to estimate uniform motion blur parameters, which improves the accuracy without any manual intervention. A single motion blurred image under spatial invariance condition is considered. It is noted that the fourth bit plane of the modified cepstrum carries an important cue for estimating the blur direction. With the exploration of this bit plane no other post processing is required to estimate blur direction. The experimental evaluation is carried out on both real-blurred photographs and synthetically blurred standard test images such as Berkeley segmentation dataset and USC-SIPI texture image database. The experimental results show that the proposed method is capable of estimating blur parameters more accurately than the existing methods.     

基于指数律分布的图像快速盲复原算法

针对现有图像盲复原迭代算法多存在耗时较长和难以保证收敛性等问题,提出一种改进的快速算法.首先根据指数律重建原始图像的频谱,然后利用原始图像和降质图像的频谱关系,采用多方向综合估计方法得到点扩散函数.多方向综合估计方法可降低估计误差,增加算法的稳定性.最后利用得到的点扩散函数和维纳滤波法进行图像重建.与现有算法的对比实验结果表明,针对适合大量成像系统的G类点扩散函数,本算法可以得到更准确的点扩散函数估计,且降低了振铃效应的影响,取得更好的图像复原效果.     

An improved Richardson-Lucy algorithm based on local prior

Ringing is one of the most common disturbing artifacts in image deconvolution. With a totally known kernel, the standard Richardson-Lucy (RL) algorithm succeeds in many motion deblurring processes, but the resulting images still contain visible ringing. When the estimated kernel is different from the real one, the result of the standard RL iterative algorithm will be worse. To suppress the ringing artifacts caused by failures in the blur kernel estimation, this paper improves the RL algorithm based on the local prior. Firstly, the standard deviation of pixels in the local window is computed to find the smooth region and the image gradient in the region is constrained to make its distribution consistent with the deblurring image gradient. Secondly, in order to suppress the ringing near the edge of a rigid body in the image, a new mask was obtained by computing the sharp edge of the image produced using the first step. If the kernel is large-scale, where the foreground is rigid and the background is smoothing, this step could produce a significant inhibitory effect on ringing artifacts. Thirdly, the boundary constraint is strengthened if the boundary is relatively smooth. As a result of the steps above, high-quality deblurred images can be obtained even when the estimated kernels are not perfectly accurate. On the basis of blurred images and the related kernel information taken by the additional hardware, our approach proved to be effective.     

Enhanced resolution for EPR imaging by two-step deblurring

The broad spectrum of spin probes used for electron paramagnetic resonance imaging (EPRI) result in poor spatial resolution of the reconstructed images. Conventional deconvolution procedures can enhance the resolution to some extent but obtaining high resolution EPR images is still a challenge. In this work, we have implemented and analyzed the performance of a postacquisition deblurring technique to enhance the spatial resolution of the EPR images. The technique consists of two steps; noniterative deconvolution followed by iterative deconvolution of the acquired projections which are then projected back using filtered backprojection (FBP) to reconstruct a high resolution image. Further, we have proposed an analogous technique for iterative reconstruction algorithms such as multiplicative simultaneous iterative reconstruction technique (MSIRT) which can be a method of choice for many applications. The performance of the suggested deblurring approach is evaluated using computer simulations and EPRI experiments. Results suggest that the proposed procedure is superior to the standard FBP and standard iterative reconstruction algorithms in terms of mean-square-error (MSE), spatial resolution, and visual judgment. Although the procedure is described for 2D imaging, it can be readily extended to 3D imaging.     

Point Spread Function Estimation for a Turbulence-Degenerated Image Based on Àtrous Wavelet Transform

The observed object images are seriously blurred because of the influence of atmospheric turbulence. The restoration is required for the reconstruction of turbulence degraded images. Point spread function (PSF) estimation, an essential part of image restoration, has no accurate estimation algorithm at present. Based on the àtrous wavelet, we deduce a novel PSF estimation algorithm. First, the àtrous wavelet at varying scales is transformed. Then, on the basis of the relation among the local maxima of the modulus of the wavelet coefficients at different scales, the Lipschitz exponent of the wavelet coefficients is computed, thus the variance of a PSF is estimated. From this estimated variance, one is able to obtain the PSF. Consequently, the object image can be restored. Experimental results show that the proposed method is highly effective with good performance.     

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。     

谱域光学相干层析系统中基于解卷积方法的像质优化

谱域光学相干层析（spectral domain optical coherence tomography, 简记为SD-OCT）系统的轴向点扩散函数（point spread function, 简记为PSF）并不具备空不变特性,无法直接应用于解卷积运算.为实现SD-OCT系统成像质量基于解卷积算法的优化,本文采用数值校正后的轴向扫描信号和轴向有效PSF来实施基于Lucy-Richardson算法的解卷积运算,进而实现了SD-OCT系统中图像质量尤其是轴向分辨率的改善.本文理论分析了SD-OCT系统中导致轴向有效PSF随成像深度增大而下降和图像模糊的因素,阐述了利用解卷积算法实现图像质量优化的过程,基于建立的SD-OCT系统实施了不同成像深度位置处PSF的标定,并利用离散轴向位置处PSF的峰值拟合了轴向有效PSF的调制函数.利用调制函数对所有轴向扫描信号进行数值校正,然后根据轴向有效PSF进行解卷积算法.典型样品的解卷积图像重建结果表明,提出的解卷积方法能有效提高系统的轴向分辨率,同时有效抑制系统灵敏度随成像深度增大而下降的趋势. 关键词： 谱域光学相干层析 Lucy-Richardson解卷积 有效点扩散函数     

谱域光学相干层析系统中基于解卷积方法的像质优化

谱域光学相干层析（spectral domain optical coherence tomography, 简记为SD-OCT）系统的轴向点扩散函数（point spread function, 简记为PSF）并不具备空不变特性,无法直接应用于解卷积运算.为实现SD-OCT系统成像质量基于解卷积算法的优化,本文采用数值校正后的轴向扫描信号和轴向有效PSF来实施基于Lucy-Richardson算法的解卷积运算,进而实现了SD-OCT系统中图像质量尤其是轴向分辨率的改善.本文理论分析了SD-OCT系统中导致轴向有效PSF随成像深度增大而下降和图像模糊的因素,阐述了利用解卷积算法实现图像质量优化的过程,基于建立的SD-OCT系统实施了不同成像深度位置处PSF的标定,并利用离散轴向位置处PSF的峰值拟合了轴向有效PSF的调制函数.利用调制函数对所有轴向扫描信号进行数值校正,然后根据轴向有效PSF进行解卷积算法.典型样品的解卷积图像重建结果表明,提出的解卷积方法能有效提高系统的轴向分辨率,同时有效抑制系统灵敏度随成像深度增大而下降的趋势.     

Parametric blur estimation for blind restoration of atmospherically degraded images: Class G

Iterative methods are typically utilized for blind image restoration (BIR); however, they are relatively slow, uncertain, and occasionally ill-behaved. This study presents a non-iterative algorithm to estimate the parameters of point spread functions (PSFs), particularly, Class G. We propose a curve model to approximate the normalized spectrum amplitude of the original image in accordance with the decay law of the natural image spectrum. The blur PSF is estimated by comparing the original image spectrum with the degraded one. Then, the image is restored by applying the estimated PSF and the Wiener filter. Experimental results demonstrate that the proposed algorithm can obtain a more accurate PSF and reduce ringing artifacts compared with the existing algorithms. The quality of the restored images is enhanced significantly.     

三维显微图像复原及点扩散函数的研究

三维显微图像去卷积计算量巨大,运算时间长。评价和分析了三维点扩散函数、散焦像、光学切片以及不同三维点扩散函数去卷积的复原图像,进一步证明了散焦光信息对焦面像的干扰,主要来自于焦面像两侧附近的散焦像。提出了折中选择三维PSF的空间大小,可以获得良好的复原效果,并且减少运行时间。提出了频谱图均值的新概念,作为评价图像清晰及模糊程度的标准,并运用于散焦像、光学切片以及复原结果图的评价。     

Blind image deconvolution using the zero-lag slice of higher-order statistics

A novel algorithm for blind image deconvolution using the zero-lag slice (ZLS) of higher-order statistics only is presented. This method first estimates the point-spread function (PSF) using the ZLS of its third-order moment (TOM) and then uses it with one of the known classical image deconvolution methods. The proposed method has simple computations for PSF estimation because it solves a nonlinear problem by using an iterative method with fast convergence. In each iteration, one need only calculate the ZLS of the TOM and estimate the PSF using simple two-dimensional operations. Furthermore, the method presented achieves good results, since the ZLS estimate obtained from the degraded image exhibits high reliability. The good performance of the proposed algorithm is demonstrated by applying it to synthetic and real data sets.