基于局部和全局信息的自适应水平集图像分割

针对仅采用局部或全局信息无法快速准确分割灰度不均匀图像的问题,提出了一种基于局部和全局信息的自适应水平集图像分割模型。首先,利用图像局部信息和全局信息建立局部能量项和全局能量项,并且利用演化曲线轮廓内外小邻域的灰度均值差作为自变量,建立了权重函数模型,实现了局部能量项和全局能量项之间权重的自适应调整,提高了模型分割灰度不均匀图像的效率和准确性。其次,提出了一种新的能量惩罚项,避免了水平集函数的重新初始化,增强了数值计算的稳定性。最后,为验证模型的优越性,将模型与CV模型、LBF模型和LGIF模型进行了对比,并通过分割时间、迭代次数以及相似度等指标对分割结果进行了客观、定量分析。最终结果表明:该模型不但对初始轮廓具有较高鲁棒性,而且对灰度不均匀图像具有较高的分割准确性与分割效率。     

利用区域信息的航拍图像分割

提出一种利用区域信息的航拍图像分割模型。针对GAC模型和Chan-Vese模型存在的不足,提出一种符号压力函数,该符号压力函数可以有效地增大模型的作用范围。与Chan-Vese模型相比,新模型不受初始条件的限制,进一步增大了模型的作用范围。新模型利用了图像的区域信息,可以同时将目标的内外边界分割出来。在新模型中,水平集函数不必初始化为符号距离函数,节省了计算开销。与传统的基于水平集方法的模型相比,新模型不含曲率项,实现简单。实验结果表明,与GAC模型和Chan-Vese模型相比,新模型的分割精度高于3%,分割速度快6倍以上。     

边缘修正CV模型的卫星遥感云图分割方法

对卫星遥感云图进行自动分割是分析卫星云图资料的重要步骤。为了更加准确的对卫星遥感云图进行分割,提出了融合边缘信息CV模型的卫星遥感云图分割方法。对原卫星云图进行扩散,得到平滑图像,根据平滑图像计算边缘信息,将得到的边缘信息融入CV模型中,并加入距离规范项使得CV模型的水平集函数在演化过程中不需要重新初始化。实验结果表明,与传统CV模型、区域能量拟合水平集模型、偏置场修正水平集模型相比,所提方法分割出的云区域更加准确,分割速度更快。     

基于改进区域项CV模型的金相图像分割

为了解决传统Chan-Vese(CV)模型难以快速、精确提取金相晶粒的问题,提出一种基于改进区域项CV模型的金相图像分割方法。该方法利用倒数交叉熵阈值选取准则函数替代传统CV模型中能量函数的区域项,构造新的水平集模型。改进模型能够使分割前后图像的倒数交叉熵达到最小,更精确地分割噪声影响严重且局部灰度变化较大的金相图像;考虑到倒数交叉熵计算会增加算法复杂度,通过引入最大绝对中位差,自适应调整曲线内外的能量权重加速曲线的演化,添加距离规范项以避免水平集函数的重新初始化,加速模型的收敛。实验结果表明,与多种模型相比,改进模型在分割结果和分割效率方面均具有明显优势。     

改进可变区域拟合模型的合成孔径声呐图像分割方法

为了自动且高精度地分割合成孔径声呐图像中的目标和阴影区域,提出一种核函数尺度自适应可变区域拟合(RSF)模型的分割方法.使用一种基于K-均值聚类的自动初始化方法对水平集进行初始化,减少了人为干预;提出改进的核函数尺度自适应RSF模型,其利用声呐成像中目标与阴影在沿扫测方向具有近似宽度的一般规律,自适应选择核函数尺度参数...     

基于改进DRLSE模型的前列腺磁共振图像分割

在图像引导下的前列腺磁共振图像分割的介入诊断与治疗具有重要意义.本文对距离正则化水平集演化（DRLSE）方法进行了改进并用于前列腺磁共振图像分割.前列腺磁共振图像中靠近膀胱一侧边界较为模糊,靠近尿道一侧及左右两侧边界较为清晰,仅用传统的梯度信息指示函数无法达到理想分割结果.本研究分别采用两个指示函数控制边界清晰段及模糊段的演化,以达到准确分割的目的.此外,还在外部能量函数中增加了能量牵制项,避免演化在虚假边界停止,驱使水平集向灰度波动较大的区域移动,并能在模糊边界停止演化.实验表明利用本方法进行前列腺磁共振图像分割的效果较好;Dice相似性系数（DSC）均值达到96%,接近专家手动分割结果.     

融入图像全局信息的局部图像拟合模型

为提高局部图像拟合(LIF)模型对初始轮廓的鲁棒性,提出了一种新的融合图像全局和局部信息的活动轮廓模型(LIF_GI模型)。针对灰度均匀图像,利用图像的全局均值构建了全局图像拟合(GIF)模型,结合GIF模型和LIF模型的优势,通过构造新的图像拟合函数构建了LIF_GI模型。为避免对水平集函数进行繁琐的重新初始化操作,使用反应扩散(RD)方法实现水平集演化。实验表明,所构建的GIF模型在灰度均匀图像上能够获得满意的分割结果,且容许灵活的轮廓初始化。在分割灰度不均匀图像时,LIF_GI模型有效地降低了LIF模型对初始轮廓的敏感性,与LIF模型相比,LIF_GI模型又表现出迭代次数少、检测速度快的优势。     

基于非凸正则化项的合成孔径雷达图像分割新算法

合成孔径雷达图像中乘性噪音的存在使合成孔径雷达图像分割变得非常困难.针对这一难题,本文以提高分割准确度,保护图像的几何结构边缘和提高算法的鲁棒性为目的,提出了一种适用于处理合成孔径雷达图像分割的新模型.新模型结合合成孔径雷达图像的区域和边缘信息,首先通过引入非凸的正则化项,定义了能量泛函;然后极小化能量泛函,建立了水平集函数演化的偏微分方程;最后对水平集演化方程的数值求解,实现了对合成孔径雷达图像感兴趣区域的分割.分别采用仿真图像和实测合成孔径雷达图像对新模型进行验证,结果表明,新模型对合成孔径雷达图像具有很强的边缘定位能力,能使目标区域分割更完整.     

基于非凸正则化项的合成孔径雷达图像分割新算法

合成孔径雷达图像中乘性噪音的存在使合成孔径雷达图像分割变得非常困难.针对这一难题,本文以提高分割准确度,保护图像的几何结构边缘和提高算法的鲁棒性为目的,提出了一种适用于处理合成孔径雷达图像分割的新模型.新模型结合合成孔径雷达图像的区域和边缘信息,首先通过引入非凸的正则化项,定义了能量泛函;然后极小化能量泛函,建立了水平集函数演化的偏微分方程;最后对水平集演化方程的数值求解,实现了对合成孔径雷达图像感兴趣区域的分割.分别采用仿真图像和实测合成孔径雷达图像对新模型进行验证,结果表明,新模型对合成孔径雷达图像具有很强的边缘定位能力,能使目标区域分割更完整.     

基于窄带多区域水平集方法的遥感图像分割

由于遥感图像存在边缘混叠等问题,经典的C-V模型会产生大量的冗余轮廓,而且无法分割多个同质区域的目标.为此,提出了基于C-V模型的窄带多区域水平集图像分割方法,采用N-1个水平集函数将图像分割成N(N＞1)个区域,每个水平集函数表达一个区域.该方法一方面通过建立独立多区域水平集模型可以消除多余的轮廓,避免分割区域的重叠...     

A novel active contour model driven by local and global intensity fitting energies

In this paper, we propose a novel hybrid active contour model for image segmentation. In our model, we define a new region-scalable fitting (RSF) energy functional which combines the local and the global image information. The RSF energy functional can not only attract the contour toward object boundaries, but also improve the robustness to initialization of the contours. In order to segment the image fast and accurately, the length term and regularization term is incorporated into the variational level set formulation. Finally, by adopting gradient descent method, the minimization of the energy equation can be given. Due to the new kernel function we defined, our model can cope with intensity inhomogeneity images and less sensitive to the initialization of the contour when compared with the other models. Experimental results demonstrated that the proposed model can also segment both the real and medical images accurately.     

Adaptive active contours based on local and global intensity information for image segmentation

This paper proposes a new formulation of active contours in the partial differential equation (PDE) framework. The evolution equation consists of two terms: a force term and a regularization term that smoothes the level set function. The proposed model can handle intensity inhomogeneity by integrating the local and global intensity information into the force term. Moreover, the level set function can be initialized to any bounded function (e.g., a constant function), thus completely eliminating the need of initial contours. Experimental results show that the proposed model can effectively and quickly segment many synthesized and real images, especially for images with intensity inhomogeneity.     

Tensor diffusion level set method for infrared targets contours extraction

A tensor diffusion level set method is presented to extract infrared (IR) targets contour under a sky-mountain-water complex background. The proposed model combines tensor diffusion operator and the eigenvalues of tensor-image into a common energy minimization level set framework. By incorporating the information of image tensor diffusion operator into the external energy term, the level set function can move in a specific way. And eigenvalues of tensor-image are used for the regularization of zero level curves in order to diminish the influence of image ‘clutter’ and noise. An additional benefit of the proposed method is robust to initial conditions. Experimental results show very good performance of the tensor diffusion level set method for IR targets contours extraction.     

Modified level set method with Canny operator for image noise removal

The level set method is commonly used to address image noise removal. Existing studies concentrate mainly on determining the speed function of the evolution equation. Based on the idea of a Canny operator, this letter introduces a new method of controlling the level set evolution, in which the edge strength is taken into account in choosing curvature flows for the speed function and the normal to edge direction is used to orient the diffusion of the moving interface. The addition of an energy term to penalize the irregularity allows for better preservation of local edge information. In contrast with previous Canny-based level set methods that usually adopt a two-stage framework, the proposed algorithm can execute all the above operations in one process during noise removal.     

Region-based object and background extraction via active contours

In this paper, we propose a region-based model for the object and background extraction with application to the image with thick or complex boundary. Based on region information of the image, we employ two curves to extract the object and background, respectively, regardless of the boundary. The first curve is used to extract the object. Correspondingly, the second curve is used to extract the background. By employing two level set functions to represent the two curves, we propose a new region-based energy functional. In the proposed model, a distance constraint term is incorporated, which effectively avoid that the two level set functions too away from each other and keep their similar shapes well. Besides, we present a penalty term to maintain the accurate computation and stability evolution. Experiment results demonstrate the desirable performance of the proposed model with application to synthetic and real-world images.     

Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method

It is a big challenge to segment magnetic resonance (MR) images with intensity inhomogeneity. The widely used segmentation algorithms are region based, which mostly rely on the intensity homogeneity, and could bring inaccurate results. In this paper, we propose a novel region-based active contour model in a variational level set formulation. Based on the fact that intensities in a relatively small local region are separable, a local intensity clustering criterion function is defined. Then, the local function is integrated around the neighborhood center to formulate a global intensity criterion function, which defines the energy term to drive the evolution of the active contour locally. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. In order to segment the image fast and accurately, we utilize a coefficient to make the segmentation adaptive. Finally, the energy is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. Experiments on synthetic and real MR images show the effectiveness of our method.     

基于水平集的闪光照相图像分割算法

针对Chan-Vese(CV)模型局部控制能力差的缺点,将基于区域的CV模型和分割曲线的局部信息结合起来,提出了一种新的水平集图像分割算法。该算法以CV法的分割曲线为初始曲线,以获得全局收敛性,在后继分割中引入分割曲线的局部信息,以提高模型对图像中微弱信号的分割能力。对闪光照相图像的数值实验表明,该算法噪声抵抗能力强,对初始轮廓位置不敏感,能实现对含细长拓扑结构和微小孔洞的弱边界闪光图像的自动分割。