基于PSO和Level Set的快速曲线演化算法

提出了一种基于微粒群算法（PSO）、水平集（Level Set）的快速曲线演化算法．该算法将图像分割分为两阶段,利用PSO方法对Snake模型中的控制点进行寻优,使控制点能快速地收敛到图像的边缘附近;利用插值算法,得到目标较粗糙的大致轮廓,以此目标轮廓作为初始的零水平集曲线;使用Level Set窄带方法得到准确的轮廓．从而克服了参数主动轮廓线模型对初始曲线敏感、噪声敏感和不能收敛到凹陷的边缘问题和几何主动轮廓线模型水平集方法计算量大等问题．实例研究结果表明了该算法的正确性、有效性．     

模糊C均值聚类与多相水平集图割优化相结合的图像分割

针对在分割多个目标时多相水平集模型对初始轮廓曲线敏感且计算量大的问题,提出采用模糊C均值聚类算法将图像进行粗分割,初始化多相水平集函数,使用图割算法分割出多相结果的方法.该方法能有效减小多相水平集算法对初始轮廓曲线的敏感性,使图割算法在分割图像时更容易分割出理想的目标轮廓;同时,采用图割算法可使水平集函数很快收敛到能量最小值,有效减少计算量,提高计算效率.实验表明该方法具有较好地分割效果和较高地分割效率.     

一种基于小波变换的目标融合跟踪方法

本文在分析小波变换的基础上，将小波分析应用到目标图像的融合跟踪技术上，利用小波的多尺度和多分辨特性，不仅能够获得不同分辨力下的图像序列，进行目标图像融合；还能有效地从信号中提取突变信号。对函数或信号进行多尺度的细化分析。图像边缘用小波变换进行处理和提取并对图像形心进行计算。能够得到较好的轮廓提取效果和形心定位精度，进而说明了小波变换可能成为目标跟踪中较好的数学方法。     

结合Zernike矩的多尺度模板形状匹配

针对形状匹配中小波表达对起始点依赖的问题,提出一种结合Zernike矩的多尺度模板进行形状匹配的方法。该算法对输入图像进行预处理后提取目标轮廓,经过归一化处理得到目标形状的平移、尺度不变的链状表达,再通过小波变换进行多尺度分析;引入Zernike矩,利用Zernike矩的特性,实现小波表达的旋转不变性,解决了小波变换对起始点的依赖。匹配过程是以小波表达的各阶Zernike矩为特征向量,在由粗到精的尺度上进行的。实验结果表明,对于同一目标,原图像与旋转不同角度的图像的正确匹配率为91％。该算法适用于轮廓较明显的目标。     

架构于抗混叠轮廓波的红外图像插值放大算法

为了在放大红外图像时保持边缘或轮廓的正则性,提出一种基于抗混叠轮廓波变换的图像插值放大算法.该算法首先结合抗混叠塔式滤波器组和方向滤波器组,构造出抗混叠的轮廓波变换;然后将原始图像的小波域线性插值结果看成是放大图像的初始估计,输入到一个迭代过程;在每次迭代中,将放大图像看成是理想高分辨率图像的含噪逼近,并对其实施抗混叠轮廓波变换,根据变换系数的稀疏性约束实现降噪处理;最后,经过若干次迭代得到理想的红外放大图像.实验表明,对于测试图像,经过迭代处理后峰值信噪比平均提高了0.837 dB;且该算法在视觉质量上明显优于双线性插值算法及基于小波的算法.     

小波多尺度改进Chan-Vese模型的红外图像分割

针对红外图像特点,提出了一种小波多尺度改进Chan-Vese模型的红外图像分割算法.首先,利用小波多尺度分析的良好信噪分离性能提取红外图像的有效边缘信息,将边缘信息添加到Chan.Vese模型的能量函数中从而提高模型的局部控制能力.同时增加内部变形能量项,约束水平集函数逼近符号距离函数,避免了水平集函数的重新初始化过程,改进了Chan-Vese模型.然后,从小波变换的顶层低频子带图像开始逐层采用改进的Chan-Vese模型分割图像,并将分割结果通过插值方式传递至下一层作为分割的初始轮廓,最终实现红外图像的分割,具有抗噪性能强和运算速度快的特点.     

小波多辨率CT成像及处理算法

分析了小波变换进行低分辨率快速图像轮廓重构和局部区域精确重构的算法。在这种算法中，滤波器与小波有关，从而可由反投影得到各种小波图像。通过小波多尺度分析和小波系数控制，提出一种简单算法进行图像增强和噪声去除。与标准的算法相比，该算法提高了重建速度和图像精度。     

基于复轮廓波变换的图像消噪

为了克服实轮廓波图像消噪后广泛存在的混叠现象,研究了基于双树复小波级联方向滤波器架构的复轮廓波变换图像消噪的若干性质,证明了对于高斯白噪声图像,该变换具有更好的分割能力和抑制能力,并在此基础上提出了一种基于该变换的图像消噪算法.该算法采用蒙特卡罗方法来确定门限收敛因子,并采用这些因子修正3σ准则,对变换域系数模值采用硬阈值处理.图像消噪实验结果表明:该消噪算法比基于实轮廓波变换的消噪算法,具有更高的峰值信噪比和更好的视觉效果.     

基于小波的多尺度SUSAN角点检测

SUSAN角点检测是一种经典的角点检测算法,但不具有尺变化特性.利用小波变换的多尺度特性,即在小尺度下的定位准确和大尺度下的抗噪性强,该文把多分辨分析的思想引入到该算法中,从而构建了一种新的基于小波变换的SUSAN多尺度角点检测算法.新的角点检测可以在不同的尺度下获取角点,克服了单一尺度的SUSAN角点检测可能存在的角点位置偏移和易受噪声干扰而提取出伪角点等问题.为了综合利用各个尺度下的角点信息,该文提出了由粗到细的角点筛选方案.通过对比实验,新算法明显地提高了图像角点检测性能.     

一种基于小波特征的彩色图像分割算法

利用小波变换的多尺度对图像纹理特征良好表达的特点,用小波变换提升算法图像纹理特征进行提取,从而达到较好的分割效果。     

A novel level set method for image segmentation by combining local and global information

A novel level set method integrating local and global statistical information is proposed in this paper. In our method, a new signed pressure force (SPF) function is constructed by two parts. One is the global average intensity of the image, which can accelerate the evolution of the curve when the contour far away from the object boundaries. The other is the intensity average of difference image between the averaging convolution image and the original image, which can guide the evolving curve to catch the boundaries of the objects. In addition, an adaptive weighting function is utilized to adjust the ratio between the global and local terms, which can eliminate the inconvenient selection of weighting parameter. By substituting the new SPF function for the edge stopping function of the geodesic active contour model, we obtain a novel adaptive hybrid segmentation model, which is capable of segmenting the images with intensity inhomogeneity. What is more, in our method, the level set function is initialized with a binary function, which reduces the computational cost for the re-initialization step. The experimental results and comparisons with several popular models on synthetic and real images indicate that our method achieves superior performance in segmenting images with noise, low contrast and intensity inhomogeneity.     

Studying Grout Propagation in Granular Soils by Image Processing Techniques

Abstract: This article presents two image‐processing techniques which allow studying grout propagation in granular soils. The first one deals with the evaluation of the cement grout concentration using UV spectrophotometry. The second is based on image segmentation processing: active contour model. We propose to develop the active contour model image analysis technique. This process, currently applied in the field of medicine, can be transposed to grout flow detection during soil injection. They are powerful image segmentation techniques that combine geometry, physics and approximation theory. Two distinct formulations exist to employ these techniques, parametric or geometric curves. These models have proven to be effective in segmenting and tracking non‐rigid structures. They exploit features derived from the image data together with a prior knowledge about the location, size and shape of these structures. We focus on a parametric approach for deformable models. They support highly intuitive interaction mechanisms. Those mechanisms allow, when necessary, researchers to bring their expertise to bear on the model‐based image interpretation task. In this paper, we show the development of the two different image analysis methods employed in our experiments for grout detection and grout concentration measurement.     

Nonlinear prediction based on a two-level markovian image model and a comparison analysis

In this article a nonlinear method of image prediction is considered. This problem arises in image coding. The method is based on a two-level statistical image model. The first level corresponds to statistical model of the contour image, and the second level corresponds to a model of brightness given the contour image. An adaptive method of image prediction is considered. Computer simulation is performed in order to compare the results of prediction in cases of linear and nonlinear predictors with both previous and surrounding pixels. Comparison is made in terms of prediction gain.     

一种改进的C-V主动轮廓模型

本文对C-V主动轮廓模型进行改进.依据曲线演化理论对C-V模型中的图像数据力驱动项进行简化,提出一种常微分方程(ODE)类型的模型.理论分析验证了该模型的水平集函数可初始化为零.与传统C-V模型相比,不但具有其特点,如可以自动检测带孔目标的内轮廓等,而且具有以下优点:抗噪性能较优;水平集函数无需重新初始化,可快速计算出全局最优分割;远离轮廓的边界可以被准确检测;时间迭代步长不受限制.对合成和真实图像的分割结果证明了本文模型具有稳健、快速的优点.     

Consideration of a CVBEM approximation for plane hydrodynamics

The complex variable boundary element method (CVBEM) represents a very useful working tool for applied mathematics in general and for hydrodynamics in particular. The goal of the present work is to give a brief survey on some approximation procedures given the data on the working domain contour in view of getting a rapid convergence of the whole process within a CVBEM. In the first section of this work we will see how some important mixed boundary value problems, for simply connected domains and for the Laplace operator, are transformed into equivalent Dirichlet problems and consequently these Dirichlet problems are the only boundary value problems we will deal with for a CVBEM. In the second section of the present work, some convergent algorithms of a CVBEM, for a Dirichlet boundary problem are built up in view of fluid dynamics (but not only!) applications.     

The Image Processing of Droplet for Evaporation Experiment in SJ-10

We have completed an experiment for droplet evaporation processing using Young-Laplace fitting, exponent fitting, polynomial fitting and ellipse fitting, which could be used for multiple shapes of droplets. The droplet evaporation experiment test was an important science experiment in SJ-10. In order to get the change process of the physical parameter, such as the touching edges and the droplet evaporation rate, we had gained the contour edge image of the droplet and used mathematic method to do the fitting analysis. The accuracy of the physical parameter was depended on the accuracy of the mathematic fitting. Using the original Young-Laplace fitting method could not process all the images of evaporation and liquid interface from the space experiment facility of SJ-10, especially the smaller droplet images. We could get more accurate contour fitting and result using the new method described in this article. This article proposes a complete solution, including edge detecting and contour fitting. In edge detecting, Canny detector was applied to extract droplet edge. In contour fitting, Young-Laplace fitting, exponent fitting, polynomial fitting and ellipse fitting are designed to fit the contour of droplets, which make the solution apply to all of droplets in SJ-10.     

Double regularization control based on level set evolution for tablet packaging image segmentation

This paper proposes a novel double regularization control(DRC) method which is used for tablet packaging image segmentation.Since the intensities of tablet packaging images are inhomogenous,it is difficult to make image segmentation.Compared to methods based on level set,the proposed DRC method has some advantages for tablet packaging image segmentation.The local regional control term and the rectangle initialization contour are first employed in this method to quickly segment uneven grayscale images and accelerate the curve evolution rate.Gaussian filter operator and the convolution calculation are then adopted to remove the effects of texture noises in image segmentation.The developed penalty energy function,as regularization term,increases the constrained conditions based on the gradient flow conditions.Since the potential function is embedded into the level set of evolution equations and the image contour evolutions are bilaterally extended,the proposed method further improves the accuracy of image contours.Experimental studies show that the DRC method greatly improves the computational efficiency and numerical accuracy,and achieves better results for image contour segmentation compared to other level set methods.     

The discrete method of separation of variables for composite material problems

In this paper, we propose the discrete method of separation of variables for the numerical solutions of the composite material problems on a polygon. After a suitable transformation of coordinates, the original boundary value problem is reduced to a discontinuous coefficients problem on a semi-infinite strip. Then we get the semi-discrete approximation of the discontinuous coefficients problem which is equivalent to a boundary value problem of a system of ordinary differential equations (O.D.E's) with constant coefficients. After solving the boundary value problem of the system by a direct method, then the semi-discrete approximation of the original problem is obtained. Especially we can see that the semi-discrete approximation in form of separable variables naturally possesses the singularity of the original problem. Finally, the numerical examples show that our method is feasible and very effective for solving composite material problems numerically.     

基于改进半因果支持域的镁熔液第一气泡检测

为精准识别镁熔液含氢量检测中镁熔液复杂表面背景下的第一气泡,在基于图像处理的镁熔液第一气泡检测算法的基础上提出了一种基于改进半因果支持域的实时检测算法.该算法首先采用改进半因果支持域模型对4帧原始图像进行估计得到背景预测图像,其次使用原始图像减去背景预测图像得到残差图像;而后利用隔帧差分算法并结合双层流水线算法获取阈值分割后的二值图像;最后对二值图像进行逻辑与运算和形态学开运算,获取真实的第一气泡目标,并在相同实验条件下将该算法对单帧图像的预处理效果、序列图像的检测性能与基于改进背景预测和流水线算法进行比较.仿真结果表明:该算法可达到实时检测的要求,且在单帧图像预处理方面对复杂背景的抑制效果更好,预处理时间减少6.2%,同时在序列图像检测方面,算法的抗干扰能力更强,检测到的目标点更易观察,检测总时间减少17.3%.