Local motion deblurring using an effective image prior based on both the first- and second-order gradients

Local motion deblurring is a highly challenging problem as both the blurred region and the blur kernel are unknown. Most existing methods for local deblurring require a specialized hardware, an alpha matte, or user annotation of the blurred region. In this paper, an automatic method is proposed for local motion deblurring in which a segmentation step is performed to extract the blurred region. Then, for blind deblurring, i.e., simultaneously estimating both the blur kernel and the latent image, an optimization problem in the form of maximum-a-posteriori (MAP) is introduced. An effective image prior is used in the MAP based on both the first- and second-order gradients of the image. This prior assists to well reconstruct salient edges, providing reliable edge information for kernel estimation, in the intermediate latent image. We examined the proposed method for both global and local deblurring. The efficiency of the proposed method for global deblurring is demonstrated by performing several quantitative and qualitative comparisons with the state-of-the-art methods, on both a benchmark image dataset and real-world motion blurred images. In addition, in order to demonstrate the efficiency in local motion deblurring, the proposed method is examined to deblur some real-world locally linear motion blurred images. The qualitative results show the efficiency of the proposed method for local deblurring at various blur levels.     

Blind image deblurring via L1-regularized second-order gradient prior

Multimedia Tools and Applications - The blind image deblurring is to find the underlying true image and the blur kernel from a blurred observation. This is a well-known ill-conditional problem in...     

基于广义规范化稀疏模型的图像盲去模糊算法

针对基于规范化稀疏先验的图像盲去模糊方法估计精度低、计算速度慢、参数选择敏感等问题,提出一种Tikhonov正则增强的广义规范化稀疏模型,且将其作为中间清晰图像和运动模糊核的共同先验约束。随后,利用算子分裂、交替方向乘子法以及快速傅立叶变换,最小化关于中间清晰图像与运动模糊核的目标函数,导出一种快速图像盲去模糊算法。在标准测试集以及实际彩色模糊图像上的实验结果验证了提出方法的有效性和鲁棒性。此外,在同等条件下与近期文献中的盲去模糊方法进行比较,显示了本文方法在估计精度和估计效率上的双重优势。     

基于独立成分分析的盲目图像反降晰

详细说明了如何将图像反降晰问题转化成独立成分分析（ICA）问题,通过理论分析和实验比较了FastICA和在线随机梯度ICA两种ICA图像反降晰算法,得出了FastICA算法并不能很好地用于图像反降晰的结论,还通过实验证实了ICA反降晰算法不能抑制噪声。最后总结了目前ICA反降晰方法的优缺点,并提出了进一步研究的方向。     

基于正则化方法的图像盲去模糊

针对标准化稀疏先验的正则化方法估计复杂模糊核时的不准确性, 引入图像的预处理, 提出了一种图像盲去模糊的新方法。该方法将图像盲去模糊分为三个步骤：利用双边滤波器和冲击滤波器对图像进行预处理, 使得图像的噪声降低、边缘突出, 有利于模糊核的估计; 对预处理后的图像, 利用基于标准化稀疏先验的正则化方法估计模糊核; 根据估计出的模糊核利用TV正则化方法对图像进行非盲去卷积。采用快速迭代收缩阈值算法和快速总变分图像复原算法分别求解模糊核估计模型和图像非盲去卷积模型。实验结果表明, 针对单幅模糊图像, 该方法可以估计出准确的模糊核, 对噪声具有鲁棒性, 并且提高了图像复原速度, 具有较好的图像恢复效果。     

Variational EM method for blur estimation using the spike-and-slab image prior

Most state-of-the-art blind image deconvolution methods rely on the Bayesian paradigm to model the deblurring problem and estimate both the blur kernel and latent image. It is customary to model the image in the filter space, where it is supposed to be sparse, and utilize convenient priors to account for this sparsity. In this paper, we propose the use of the spike-and-slab prior together with an efficient variational Expectation Maximization (EM) inference scheme to estimate the blur in the image. The spike-and-slab prior, which constitutes the gold standard in sparse machine learning, selectively shrinks irrelevant variables while mildly regularizing the relevant ones. The proposed variational Expectation Maximization algorithm is more efficient than usual Markov Chain Monte Carlo (MCMC) inference and, also, proves to be more accurate than the standard mean-field variational approximation. Additionally, all the prior model parameters are estimated by the proposed scheme. After blur estimation, a non-blind restoration method is used to obtain the actual estimation of the sharp image. We investigate the behavior of the prior in the experimental section together with a series of experiments with synthetically generated and real blurred images that validate the method's performance in comparison with state-of-the-art blind deconvolution techniques.     

可学习高阶微分方程的图像盲复原

目的 图像盲复原是图像处理中的常见的重要问题之一,具有巨大的研究价值和广泛的应用。通常情况下,相机抖动,聚焦不准,环境噪声等因素都会造成图像模糊。由于图像盲复原需要同时求解模糊核和清晰图像,导致该问题是病态的而难于求解。现有的盲复原方法可以分为两大类,一类是基于最大后验概率来同时估计潜在图像和模糊核的方法,但是这样耦合在一起的方法由于先验条件和初值设置不恰当,常常会导致最终求得的是问题的平凡解,以至于盲复原的效果并不理想。另一类是基于变分贝叶斯来估计模糊核,这种方法通常是采用最大化强边图像的边缘概率,由此估计的模糊核鲁棒性较强,但是对潜在图像的强边条件要求比较高,计算复杂度和实现难度都较大。鉴于以上方法的优缺点,提出基于高阶微分方程学习的方法来实现图像去模糊。方法 借鉴传统的迭代演化方法和网络学习方法各自的优势,将网络学习到的特征（引导图像,卷积滤波器,稀疏测度）融入到高阶微分方程的演化过程中区,提出可学习的基于高阶微分方程的演化来模拟图像的演化过程。具体地,先用范数约束得到一个粗略的强边引导图像,然后将学习到的卷积滤波器和稀疏函数一起作用在当前的潜在图像上,得到一个关于图像的更好的梯度下降方向,将此作为微分方程演化的一个步骤,得到一个更为精炼的强边图像。最后用精炼的强边图像来估计模糊核。该方法可以通过先验知识和训练数据来有效地控制模糊核的估计,进而得到较为清晰的盲复原结果。结果 在图像建模层面上,用非盲复原的方法验证了本文提出的微分方程演化过程是可行的。通过和其他盲复原方法做对比,在不同的基准图像数据库上的定量的实验中,本文方法在数据库上的峰值信噪比,结构相似度分别达到30.30,0.91,误差率低至1.24;比其他方法的结果都要好,在时间上,虽然我们的算法不是用时最少的,但是和性能相当的本文的方法相比,本文算法时间消耗远比该算法少。在各种不同类型的模糊图像去模糊结果也表明了本文方法是有效的。结论 本文可学习的高阶微分方程去模糊的方法,能够有效地估计模糊核,进而更好地恢复出清晰图像。实验结果表明本文方法在各种场景中具有较高的灵活性,都能自适应地对图像去模糊。     

利用拉氏算子鉴别运动模糊方向

提出一种新的鉴别运动模糊图像的运动模糊方向的方法,它利用拉氏算子对运动模糊图像进行无方向性的二阶微分,并求微分图像的自相关,发现自相关图像中数值较大的点(鉴别点)能够有效标示出运动模糊方向。选取适当数目的候选鉴别点,并利用聚类方法剔除其中的奇异点,得到鉴别点;过零频尖峰(自相关图像的中心点)画一条直线,计算各个鉴别点到该直线的距离,求距离和;改变直线方向,当距离和最小时,直线的方向即为运动模糊方向。数据实验表明,这一新的运动模糊方向鉴别方法,具有抗噪声能力强、适用范围广、计算量小、鉴别精度高、稳定性好的优点．     

加强边缘感知的盲去模糊算法

目的 拍摄过程中,如果摄像机进行了错误的聚焦,就会得到模糊的图像,如何将模糊图像变得清晰成为一个亟待解决的问题。目前关于图像的去模糊方法多采用基于模糊核约束的卷积模型。但是由于实际应用中很难准确获取模糊核的信息,同时计算机也存在精度限制,计算结果与实际物理模型有偏差,因而去模糊的主要挑战为：如何精确地估计模糊核,以及如何在复原过程中减弱由于精度限制造成的振铃效应。方法 振铃效应是指图像的灰度剧烈变化处产生的震荡,类似于钟被敲击后产生的波状空气震荡。在图像复原过程中,此效应通常发生在梯度变化较大的边缘区域附近。本文对此进行研究,在去模糊过程中引入边缘信息作为约束条件,以改善模糊核的估计,并通过抑制边缘区域的反卷积,抑制图像复原过程中的振铃效应。算法主要分为如下3个部分：1）设计了适用于模糊图像的边缘提取算法;2）利用边缘信息设计了加强边缘感知的反卷积算法;3）提出并设计了安全检测子,以保证算法在边缘区域复原的完整性。结果 实验结果表明,在没有先验知识的情况下,本文方法可以较好地恢复图像细节,并有效抑制振铃效应。较之传统的去模糊处理算法,本文方法在性能上有较大提高。比如,相比于Chan、Krishnan以及Hu的方法,本文方法在峰值信噪比指标上分别提高了25.73%、3.52%和4.43%,在结构相似性指标上分别提高了7.67%、1.63%和3.59%。同时,与基于深度学习的方法相比,本文方法不依赖于数据集,鲁棒性更强。结论 本文方法可以较好地恢复图像细节,并抑制振铃效应,同时比深度学习方法适用范围更广。     

Non-uniform image deblurring using an optical computing system

Removing non-uniform blur caused by camera shaking is troublesome because of its high computational cost. We analyze the efficiency bottlenecks of a non-uniform deblurring algorithm and propose an efficient optical computation deblurring framework that implements the time-consuming and repeatedly required modules, i.e., non-uniform convolution and perspective warping, by light transportation. Specifically, the non-uniform convolution and perspective warping are optically computed by a hybrid system that is composed of an off-the-shelf projector and a camera mounted on a programmable motion platform. Benefitting from the high speed and parallelism of optical computation, our system has the potential to accelerate existing non-uniform motion deblurring algorithms significantly. To validate the effectiveness of the proposed approach, we also develop a prototype system that is incorporated into an iterative deblurring framework to effectively address the image blur of planar scenes that is caused by 3D camera rotation around the x-, y- and z-axes. The results show that the proposed approach has a high efficiency while obtaining a promising accuracy and has a high generalizability to more complex camera motions.     

基于稀疏表示的单帧运动图像盲复原

提出一种基于稀疏表示的单帧运动盲复原方法,它充分利用自然图像中存在的各种先验知识进行求解。该方法分为模糊核估计和图像修复两个阶段。在估计模糊核时,它运用shock滤波器从模糊图像中预测出清晰边缘,以此指导全局图像的复原,并运用多尺度策略来解决大模糊核问题。在图像修复阶段,运用稀疏表示理论对复原图像进行降噪和重建,最终提高图像复原质量。实验结果表明,在不同噪声和模糊核条件下,该算法能有效消除运动模糊。     

运动模糊图像的质量分析与评价

提出了一种新的图像质量评价标准,通过图像的运动模糊参数来估计出图像由于运动而造成的信息损失量,并通过信息损失的多少来评价图像的质量。实验表明,该方法能客观地体现出运动模糊图像的质量与运动模糊参数之间的关系,这种关系对于图像的质量评价特别是有参考条件下的图像质量评价具有良好的效果。同时还根据活动度和图像灰度梯度能客观地表示图像细节部分的特性。将图像分块,并从8个方向对图像进行分析,客观地评价出无参考条件下直线运动模糊图像的质量。     

图像运动模糊方向的检测方法

为了降低运动模糊图像恢复问题的复杂度,提高计算效率,将图像恢复的二维问题转化为一维问题,可以将图像的模糊方向旋转到水平方向,这就需要识别图像的运动模糊方向.计算模糊图像任意角度的方向微分,根据微分图像灰度值的绝对值的分布特征,可以看到模糊方向和微分图像的绝对灰度值存在一定的关系,由此可以鉴别出模糊方向.在鉴别过程中,给出了精度更高的三次样条插值计算微分图像的详细方法.仿真实验表明,该方法稳定性好,具有较高的精度.     

Real-time motion blur using extruded triangles

Several algorithms have been introduced to render motion blur in real time by solving the visibility problem in the spatial-temporal domains. However, some algorithms render at interactive frame rates but have artifacts or noise. Therefore, we propose a new algorithm that renders real-time motion blur using extruded triangles. Our method uses two triangles in the previous frame and the current frame to make an extruded triangle then send it to rasterization. By using the standard rasterization, visibility determination is performed efficiently. To solve the occlusion between extruded triangles for a given pixel, we introduce a combination solution using a sorting in front-to-back order and bitwise operations in the spatial-temporal dimensions. This solution ensures that only non-occluded extruded triangles are shaded. We further improve performance of our algorithm using a coverage map.     

Blind image deblurring via gradient orientation-based clustered coupled sparse dictionaries

Pattern Analysis and Applications - In this paper, we proposed a novel sparse representation-based blind image deblurring algorithm, which exploits the benefits of coupled sparse dictionary, and...     

Accurate blind deblurring using salientpatch-based prior for large-size images

The full-image based kernel estimation strategy is usually susceptible by the smooth and fine-scale background regions impacting and it is time-consuming for large-size image deblurring. Since not all the pixels in the blurred image are informative and it is frequent to restore human-interested objects in the foreground rather than background, we propose a novel concept “SalientPatch” to denote informative regions for better blur kernel estimation without user guidance by computing three cues (objectness probability, structure richness and local contrast). Although these cues are not new, it is innovative to integrate and complement each other in motion blur restoration. Experiments demonstrate that our SalientPatch-based deblurring algorithm can significantly speed up the kernel estimation and guarantee high-quality recovery for large-size blurry images as well.     

Improved scheme of estimating motion blur parameters for image restoration

A motion deblurring algorithm is proposed to enhance the quality of restoration based on the point spread function (PSF) identification in frequency spectrum. An improved blur angle identification algorithm characterized by bilateral-piecewise estimation strategy and the membership function method is presented by formulating the edges of the central bright stripe. Subsequently, the subpixel level image generated with bilinear interpolation is employed in the blur length estimation by calculating the distance between two adjacent dark strips. Through comparison with the existing algorithms, experimental results demonstrate that the proposed PSF estimation scheme could not only achieve higher accuracy for the blur angle and the blur length, but also produce more impressive restoration results. Furthermore, the robustness of our method is also validated in different noisy situations.     

拉普拉斯与双边滤波的图像去运动模糊算法

运动模糊图像盲复原是图像复原中的关键问题之一,由于模糊信息的复杂性以及图像噪声的影响,导致复原的结果有振铃效应.为解决这些问题,提出基于拉普拉斯先验的改进算法.在原有的模糊核估计过程中,引入拉普拉斯锐化增强,增强图像的边缘信息,达到改善模糊核估计结果的目的.在复原时,针对图像振铃噪声,引入了双边滤波,抑制该噪声对复原结果的影响,进一步改善复原图像的质量.与三种现有图像去模糊算法相比,该方法能更准确地估计模糊信息,对图像复原具有更好的鲁棒性.     

Recognition of camera-captured low-quality characters using motion blur information

Camera-based character recognition has gained attention with the growing use of camera-equipped portable devices. One of the most challenging problems in recognizing characters with hand-held cameras is that captured images undergo motion blur due to the vibration of the hand. Since it is difficult to remove the motion blur from small characters via image restoration, we propose a recognition method without de-blurring. The proposed method includes a generative learning method in the training step to simulate blurred images by controlling blur parameters. The method consists of two steps. The first step recognizes the blurred characters based on the subspace method, and the second one reclassifies structurally similar characters using blur parameters estimated from the camera motion. We have experimentally proved that the effective use of motion blur improves the recognition accuracy of camera-captured characters.     

利用频谱特性鉴别运动模糊方向

点扩展函数(PSF)的精确估计是运动模糊图像恢复的关键。匀速直线运动模糊的PSF参数主要由模糊角度（方向）和模糊尺度两个参数组成,然而模糊角度的估计又是重中之重。针对R Lokhande等人提出的霍夫变换的运动模糊方向估计法进行改进,通过增加边缘检测等预处理步骤,利用霍夫变换检测直线,并利用改进的霍夫变换峰值提取方法来估计角度值。实验表明,该方法能够得到比原方法更精确的角度值,并且具有抗噪能力强、鉴别精度高的优点。