基于ARTUR算法的气动光学效应图像校正方法

提出了一种基于ARTUR算法的气动光学效应图像校正方法。该方法利用一些合理的先验知识对大气扰动退化模型(点扩展函数)进行规化,将求解问题转化为带惩罚项的准则函数的优化估计问题,通过ARTUR算法快速迭代估计点扩展函数值,进而对气动光学效应引起的退化图像进行校正。论述了ARTUR算法的性质,给出了实验结果。     

一种改进的FCM算法在脑出血图像中的应用

CT图像在人体脑出血的诊断中起着关键的作用,因此利用计算机对医学CT图像进行辅助处理具有非常重要的意义.为提高计算机辅助诊断的准确性,本文提出一种考虑空间信息的FCM(fuzzy c-means)算法.在Ahmed、Yamany等人提出的FCM_S(FCM _Spatial)[1]算法基础上引入了空间距离因素,在抑制噪...     

基于HOUGH变换的QPSK信号盲处理结果可信性评估

本文研究了QPSK信号盲处理结果的可靠性检验问题,提出了一种基于HOUGH变换的检验算法。该方法可在缺乏信号先验知识的条件下,利用盲处理结果并根据调制识别结果对应的信号模型构造辅助信号,将辅助信号与观测信号相关累加。在分析不同可信性假设下相关累加模值曲线特征的基础上,通过对HOUGH变换极值点聚类数是否为1的检验,来实现对信号盲处理的可信性检验。计算机仿真结果表明,本算法在较低信噪比条件下,可实现对QPSK信号盲处理结果的可信性校验。     

（论坛）基于全变分的模糊人脸图像复原算法

在人脸图像采集过程中,会受到多种因素影响,图像质量都会有所退化,因此将模糊图像恢复成清晰图像一直是图像处理领域的热点之一。根据全变分正则化的图像复原算法的思想,引入相容点集与不相容点集的概念,以及一些辅助的约束条件,提出一种有约束人脸图像复原优化模型,并使用最速下降法求解此模型,使模糊的人脸图像清晰化。实验结果表明,这种模型是可行的,基本恢复了原始的图像。     

反坦克导弹电视制导图像处理系统设计

根据反坦克导弹电视制导要求,设计了由视频预处理和背景减法电路模块、数字图像处理模块和其他辅助功能模块组成的图像处理系统硬件部分,介绍了这些模块的作用和功能;设计了包含图像预处理、目标分割、目标识别和目标跟踪等功能的图像处理系统软件部分,特别对图像目标的多模阈值分割和识别跟踪处理方法进行了阐述,给出了实验结果。实验结果表明,该系统能可靠识别和跟踪反坦克导弹。     

MAP estimation for hyperspectral image resolution enhancement using an auxiliary sensor

This paper presents a novel maximum a posteriori estimator for enhancing the spatial resolution of an image using co-registered high spatial-resolution imagery from an auxiliary sensor. Here, we focus on the use of high-resolution panchomatic data to enhance hyperspectral imagery. However, the estimation framework developed allows for any number of spectral bands in the primary and auxiliary image. The proposed technique is suitable for applications where some correlation, either localized or global, exists between the auxiliary image and the image being enhanced. To exploit localized correlations, a spatially varying statistical model, based on vector quantization, is used. Another important aspect of the proposed algorithm is that it allows for the use of an accurate observation model relating the "true" scene with the low-resolutions observations. Experimental results with hyperspectral data derived from the airborne visible-infrared imaging spectrometer are presented to demonstrate the efficacy of the proposed estimator.     

基于变步长搜索黄金分割优化的自聚焦算法

为了获得高分辨的合成孔径雷达(SAR)图像,需采用自聚焦算法对SAR图像进行处理。文中介绍了利用图像对比度最优准则进行自聚焦的原理方法,将对比度最优自聚焦过程等效为最优一维搜索模型。同时,介绍了变步长搜索黄金分割算法的原理,首先通过变步长搜索确定搜索区间,然后采用黄金分割法进行迭代收敛,当满足终止条件时,停止迭代并得到最终的多普勒调频率最优估计值。与现有的算法相比,基于变步长搜索黄金分割优化的自聚焦算法具有收敛速度快、鲁棒性强的优点。实测数据处理结果验证了算法的有效性。     

一种消除光照影响的舰船跑道区域增强方法

光照过强或者过弱都会对舰船跑道直线提取造成严重影响,导致跑道直线提取不完全甚至失败。针对上述情况,提出了一种图像处理算法来消除光照带来的影响同时增强跑道直线的算法。首先将图像灰度均值恢复到光照合适时的水平,然后用一种线性灰度变换算法增大图像的动态范围和对比度,并且根据图像质量改善情况的反馈对这两步多次迭代,直至得到较好的图像跑道增强效果。仿真实验证明该算法较好地消除了光照变化带来的不利影响,并实现了增强舰船跑道线的目的。     

Using anisotropic diffusion equations in pixon domain for image de-noising

Image enhancement is an essential phase in many image processing algorithms. In any image de-noising algorithm, it is a major concern to keep the interesting structures of the image. Such interesting structures in an image often correspond to the discontinuities in the image (edges). In this paper, we propose a new algorithm for image de-noising using anisotropic diffusion equations in pixon domain. In this approach, diffusion equations are applied on the pixonal model of the image. The algorithm has been examined on a variety of standard images and the performance has been compared with algorithms known from the literature. The experimental results show that in comparison with the other existing methods, the proposed algorithm has a better performance in de-noising and preserving image edges.     

一种基于Poisson方程的分离型图像修复方法

图像修复是一种恢复图像中损坏部分的技术,具有广泛的应用.基于采样复制的修复方法对纹理图像有较好的效果,但容易产生块效应,而且对结构信息的修复可能产生较大的偏差.本文提出了一种基于Poisson方程的分离型修复算法,首先将原图分解为结构图像和纹理图像两部分,然后根据其特件分别进行修复,叠加后得到最终的修复结果.对结构图像使用Laplacian算子强化结构信息,然后对Laplacian场进行修复并使用Poisson方程重建,可以同时保持锐利的区域边界以及平滑的区域背景.实验表明该方法可以有效改善修复的视觉效果,对大区域修复也有良好的表现.     

Image Segmentation Using Information Bottleneck Method

In image processing, segmentation algorithms constitute one of the main focuses of research. In this paper, new image segmentation algorithms based on a hard version of the information bottleneck method are presented. The objective of this method is to extract a compact representation of a variable, considered the input, with minimal loss of mutual information with respect to another variable, considered the output. First, we introduce a split-and-merge algorithm based on the definition of an information channel between a set of regions (input) of the image and the intensity histogram bins (output). From this channel, the maximization of the mutual information gain is used to optimize the image partitioning. Then, the merging process of the regions obtained in the previous phase is carried out by minimizing the loss of mutual information. From the inversion of the above channel, we also present a new histogram clustering algorithm based on the minimization of the mutual information loss, where now the input variable represents the histogram bins and the output is given by the set of regions obtained from the above split-and-merge algorithm. Finally, we introduce two new clustering algorithms which show how the information bottleneck method can be applied to the registration channel obtained when two multimodal images are correctly aligned. Different experiments on 2-D and 3-D images show the behavior of the proposed algorithms.     

小波变换和改进的FCM算法在医学CT图像分割中的运用

为了更好地运用电脑技术辅助医学诊断,本文研究了一项在小波变换和改正的模糊C均值PCM算法基础上进行医学CT图像分割的方法,以FCM算法为基础,采取小波变换方式针对医学CT图像展开分解,之后运用分解后的低频图的像素点来作为FCM算法的基础点,然后运用马氏距离来进行进一步修正,从而确保更加准确的反应医学图像中的信息.研究结果显示,通过这一方法的处理,医学CT的效果得到了很大的提升.     

An expanded theoretical treatment of iteration-dependent majorize-minimize algorithms.

The majorize-minimize (MM) optimization technique has received considerable attention in signal and image processing applications, as well as in statistics literature. At each iteration of an MM algorithm, one constructs a tangent majorant function that majorizes the given cost function and is equal to it at the current iterate. The next iterate is obtained by minimizing this tangent majorant function, resulting in a sequence of iterates that reduces the cost function monotonically. A well-known special case of MM methods are expectation-maximization algorithms. In this paper, we expand on previous analyses of MM, due to Fessler and Hero, that allowed the tangent majorants to be constructed in iteration-dependent ways. Also, this paper overcomes an error in one of those earlier analyses. There are three main aspects in which our analysis builds upon previous work. First, our treatment relaxes many assumptions related to the structure of the cost function, feasible set, and tangent majorants. For example, the cost function can be nonconvex and the feasible set for the problem can be any convex set. Second, we propose convergence conditions, based on upper curvature bounds, that can be easier to verify than more standard continuity conditions. Furthermore, these conditions allow for considerable design freedom in the iteration-dependent behavior of the algorithm. Finally, we give an original characterization of the local region of convergence of MM algorithms based on connected (e.g., convex) tangent majorants. For such algorithms, cost function minimizers will locally attract the iterates over larger neighborhoods than typically is guaranteed with other methods. This expanded treatment widens the scope of the MM algorithm designs that can be considered for signal and image processing applications, allows us to verify the convergent behavior of previously published algorithms, and gives a fuller understanding overall of how these algorithms behave.     

子阵级和差及辅助波束联合自适应单脉冲方法

数字阵列雷达在每一个阵元后有一个接收通道,若采用全自适应处理,则计算复杂度高,难以满足实时性需求。因此,对于实际的系统往往要采用降维自适应阵列处理去解决以上问题。鉴于此,提出一种子阵级和差及辅助波束联合自适应单脉冲算法。该方法基于子阵降维情况下,利用子阵合成的高增益差波束以及若干子阵合成的指向若干副瓣干扰(SLJ)方向的辅助波束来对消主副瓣干扰。理论分析和仿真结果均表明,该方法不仅在有效抑制主副瓣干扰的同时保证了高精度的单脉冲测角能力,并且进行子阵降维处理解决了相控阵体制雷达阵元数繁多所带来的问题,便于工程实现。     

基于PC-MSPCNN模型和SLIC的彩色图像分割方法

针对简单线性迭代聚类(SLIC)方法对图像边缘细节处理效果不佳的问题,提出一种参数可控、改进的简化脉冲耦合神经网络模型(PC-MSPCNN)与SLIC结合的彩色图像分割方法。该方法首先改进MSPCNN模型的加权矩阵和连接系数,并增设辅助参数,以提高分割准确度。随后将彩色图像输入至PC-MSPCNN模型中,依据改进模型中输出Y值的分布划分物体的边缘,使分割结果更好地贴合物体的边缘,利用所提出的相似性准则合并散布的碎片,减小后续处理的复杂度;其次,在SLIC度量相似距离的基础上引入PC-MSPCNN中RGB三个通道的内部活动项U值,完成对图像剩余部分的加权融合聚类,改进聚类效果。实验结果表明,本文方法能更精确地贴合图像中物体的边界,大幅减少碎片,有效提高图像的边缘贴合度。     

一种维特比译码器的矩阵实现方案

本文针对(2,1,l)卷积码提出一种维特比矩阵译码算法,通过引入整形、合并和动态选择等辅助模块,实现了所有环节的矩阵处理,构建出具有单一结构的并行译码器。由于只需要更改一部分模块的内部参数便可获得不同卷积码译码器,因此非常有利于分析和设计。仿真实验表明,在运算量更少的情况下,矩阵译码器可以取得接近最优的译码性能。     

航天湍流退化图像的极大似然估计规整化复原算法

为了从有噪的湍流退化图像中有效地恢复出目标图像，提出了一种基于极大似然估计准则的规整化复原算法．根据图像随机场模型建立了有关多帧图像数据的对数似然函数，同时为了平滑噪声和保护图像边缘以及避免无价值的解，将一些合理的惩罚项和辅助平滑项融合到该对数似然函数中．推导出了湍流点扩展函数和目标图像的交替迭代求解公式，通过迭代方式可将点扩展函数和目标图像同时估计出来，给出了算法的并行处理方案．在微机上对强噪声条件下的湍流退化图像进行了恢复实验，实验结果表明本算法具有较强的抗噪能力和实用价值．     

基于分裂Bregman方法的全变差图像去模糊

针对全变差图像去模糊问题,提出一种基于分裂Bregman方法的全变差图像去模糊算法,利用分裂Bregman方法来优化其求解问题模型.首先,利用辅助变量及其二次惩罚泛函把全变差去模糊优化问题转化为一个等价的无约束优化问题;其次,基于Bregman迭代将其分解为两个子优化问题采用交替最小化方法进行求解;最后,根据子问题结构特点,采用离散傅立叶变换及收缩技术实现子优化问题的快速计算.实验结果表明,在不同尺寸模糊核条件下本文算法能获得有效、稳定的图像复原结果,相比FTVd、IRN去模糊方法,本文算法复原效果更好,计算更加快速.     

A wavelet approach for the identification of axonal synaptic varicosities from microscope images.

Direct visualization of synapses is a prerequisite to the analysis of the spatial distribution patterns of synaptic systems. Such an analysis is essential to the understanding of synaptic circuitry. In order to facilitate the visualization of individual synapses at the subcellular level from microscope images, we have introduced a wavelet-based approach for the semiautomated recognition of axonal synaptic varicosities. The proposed approach to image analysis employs a family of redundant wavelet representations. They are specifically designed for the recognition of signal peaks, which correspond to the presence of axonal synaptic varicosities. In this paper, the two-dimensional image of an axon together with its synaptic varicosities is first transformed into a one-dimensional (1-D) profile in which the axonal varicosities are represented by peaks in the signal. Next, by decomposing the 1-D profile in the differential wavelet domain, we employ the multi-scale point-wise product to distinguish between peaks and noises. The ability to separate the true signals (due to synaptic varicosities) from noise makes possible a reliable and accurate recognition of axonal synaptic varicosities. The proposed algorithms are also designed with a variable threshold that effectively allows variable sensitivities in varicosity detection. The algorithm has been systematically validated using images containing varicosities (< or =30) that have been consistently identified by seven human observers. The proposed algorithm can give high sensitivity and specificity with appropriate threshold. The results have indicated that the semiautomatic approach is satisfactory for processing a variety of microscopic images of axons under different conditions.     

基于小波变换与像元对目标的短波红外图像增强算法

弱光夜视是短波红外成像的重要应用领域之一。针对短波红外弱光图像对比度低,增强后噪声也被放大的特点,提出了一种基于小波变换与像元对目标的短波红外图像增强算法。首先通过小波变换获得不同频率成分的子带图像;然后对低频子带图像进行基于像元对目标的灰度变换处理,对高频子带图像进行可变阈值降噪处理;最后通过小波反变换将处理后的子带重构得到增强结果。将该算法与基于直方图的增强算法,全局优化线性窗口色调映射算法和自然保持增强算法进行比较,采用图像的信息熵和基于Michelson法则的对比度增强度量作为客观评价指标,结果表明本文算法更为有效地提高了短波红外弱光图像的对比度,抑制了噪声的增强,提升了图像的视觉效果。