基于边缘和区域信息相结合的变分 水平集图像分割方法

 针对GAC模型和C-V模型分别存在对弱边缘和灰度渐进图像分割效果不理想以及演化效率低等问题,提出了一种基于边缘和区域信息相结合的变分水平集图像分割方法.结合了图像边缘梯度信息和区域全局信息的能量函数作为模型的外部能量项,引入内部变形能量约束水平集函数来逼近符号距离函数,省去了重新初始化水平集函数的过程,并融入了物体形状先验知识的附加约束信息,提高了分割精度.实验结果表明,论文所用方法对分割噪声弱边缘图像和灰度渐进图像具有一定的有效性和可行性.     

基于改进水平集方法的粘连细胞分割

传统水平集方法对粘连细胞分割效果差,同时在分割过程中需要不断地重新初始化水平集函数。为了解决传统水平集方法在粘连细胞分割上的不足,提出了一种基于颜色特征的水平集方法。该方法将能够约束水平集函数与符号距离函数之间偏差的变分公式作为内部能量项,从而无需重新初始化水平集函数;把结合图像颜色特征信息的能量函数作为模型的外部能量项,以改进粘连细胞的分割效果。实验结果表明,该方法能有效地分割粘连细胞,算法实现比较简单。     

距离保持水平集在汽车门锁图像分割中的应用研究

针对基于机器视觉的汽车门锁装配尺寸检测系统中摇臂距离的检测问题,研究了距离保持水平集的图像分割算法。该算法是将轮廓表示为一个符号函数,符号函数的零水平面与实际轮廓相对应,并在能量泛函中加入了内部能量泛函,表示两个函数之间的差异。实验表明,与一般的基于边缘检测的图像分割算法相比较,该算法能够很好的解决汽车门锁图像中摇臂外弧线分割问题,提高了汽车门锁检测系统的精度。同时,该算法也可应用到其他类似工业装配件局部图像分割中。     

一种基于变分水平集的红外图像分割算法

红外图像大都存在边缘模糊或离散状边缘的特点,并且图像的先验知识较少,因此红外图像的分割是比较困难的。针对这种情况,该文提出了一种基于图像全局信息并且不需要重新初始化的变分水平集红外图像分割方法,不考虑图像边缘梯度的影响,将图像全局信息作为外部能量项,在很大程度上克服了边缘模糊时过分割的情况。同时通过引入内部变形能量约束水平集函数逼近符号距离函数,省去了重新初始化水平集函数的过程,简化了计算,减小了因重新初始化水平集函数带来的误差。将算法应用在红外图像的分割中,验证了算法的有效性。     

结合局部能量与改进的符号距离正则项的图像目标分割算法

针对传统C-V模型对颜色不均匀图像分割失败并且对初始轮廓和位置敏感问题,以及现有符号距离正则项存在周期性振荡和局部极值问题。该文提出结合局部能量信息和改进的符号距离正则项的图像目标分割算法。首先,将全局图像信息扩展到HSV空间,并使用局部能量项信息分析每个像素及其领域内的统计特性,从而在较少的迭代次数内有效分割颜色分布不均匀图像。其次,改进现有符号距离正则项,改进后的符号距离正则项在避免水平集函数的重新初始化的同时,提高了计算效率,保证了水平集函数演化过程的稳定性。然后,定义阈值判断法的水平集函数演化的终止准则,使曲线准确演化到目标轮廓。该算法与同类模型的对比实验表明该模型具有较高的分割精度和对初始轮廓的鲁棒性。     

水平集方法中符号距离函数快速重构

符号距离函数重构是水平集方法中必不可少、且相当费时的步骤。本文分类比较了符号距离函数的构造方法;对两类快速算法:基于程差方程的显式方法和基于偏微分方程的隐式方法,进行不同程度的改进;通过对比实验验证算法有效性,从实验结果分析了各方法的优缺点。最后介绍两类方法在水平集方法图像分割中的具体应用。     

一种新的基于水平集方法的SAR图像分割算法

本文基于Aubert-Aujol（AA）模型和变分水平集方法提出一个新的SAR图像分割模型;在反应-扩散框架下,将各项同性扩散算子加入到该模型的水平集演化方程中,并提出一个两步分裂水平集演化算法,该算法不需要周期性地更新水平集函数。通过对合成图像和Envisat SAR图像的分割实验,表明本文提出的算法具有较准确的边缘定位能力和噪声抑制能力。     

一种新的SAR图像局部拟合活动轮廓模型

本文基于I-divergence-TV(IDT)去噪模型和变分水平集方法提出一个新的局部拟合活动轮廓模型。该模型能有效解决SAR图像的分割问题,并且不需要周期性地更新水平集函数。通过对合成图像和实测Envisat SAR图像的分割实验,提出的模型与局部拟合RSF模型相比具有更准确的边缘定位能力和噪声抑制能力。     

一种改进的单参数水平集快速分割方法

针对传统水平集分割方法的参数多且速度较慢的问题,提出了一种新的基于单参数的快速水平集图像分割方法,改进了基于Mumford-Shah模型的Chan-Vese(C-V)模型,引入惩罚函数项、用水平集函数梯度的模取代Dirac函数,并且只保留长度项参数,构造出无须重新初始化且具有全局优化的新模型。此外,在算法实现中引入停止迭代判定式,实现自动分割同时得到单参数的取值规律。人工合成图像和医学图像分割的实验结果表明,该方法具有更快的速度和更好的鲁棒性。由于零水平集函数可以任意设定且便于调整单参数取值,新方法具有更广泛的适应性。     

基于Chan-Vese模型的树形结构多相水平集图像分割算法

由于Chan-Vese(C-V)模型通过单个水平集的符号将待分割图像划分为目标和背景两个部分,所以当图像的多个目标的轮廓成多连接时,C-V模型将无法表示.为了解决C-V模型在表示目标轮廓上的局限,提出了基于C-V模型的树形结构多相水平集算法.关键策略是通过改变图像背景,使得水平集在新图像上重新收敛;核心技术是依据同时明度对比提出的背景填充技术;算法流程采用多水平集串行收敛方式实现多相分割(n-1次收敛可以实现n相分割,n＞1).实验结果表明,本算法可以表示复杂的区域连接情况(n相分割最多可以表示n连接情况),能够实现多目标分割(n相分割可以实现n-1个目标分割),特别适合于目标中含有子目标的图像.     

Surface Function Actives

Deformable models have been widely used in image segmentation since the introduction of the snakes. Later the introduction of level set frameworks to solve the energy minimization problem associated with the deformable model overcame some limitations of the parametric active contours with respect to topological changes by embedding surface representations into higher dimensional functions. However, this may also bring in more computational load so that recent advances in spatio-temporal resolutions of 3D/4D imaging raised some challenges for real-time segmentation, especially for interventional imaging. In this context, a novel segmentation framework, Surface Function Actives (SFA), is proposed for real-time segmentation purpose. SFA has great advantages in terms of potential efficiency, based on its dimensionality reduction for the surface representation. Utilizing implicit representations with variational framework also provides flexibility and benefits currently shared by level set frameworks. An application for minimally-invasive intervention is shown to illustrate the potential applications of this framework.     

Variational level set method for image segmentation with simplex constraint of landmarks

Landmarks are prior image features for a variety of computer vision tasks. In the image processing domain, research on image segmentation methods has always been a significant topic. Due to the image characteristics of heterogeneous nature, lack of clear boundaries, noise and so on, accurate segmentation of the image is still a challenge. In this paper, utilizing a level set framework and the simplex constraint, preferred image point landmarks are combined into a variational segmentation model to enforce the contour evolve with prior points. Then the alternating minimization algorithm of the proposed model is designed, meanwhile the landmarks constraints are doubled ensured with simplex projection. Finally, experiments on many synthetic and real-world images were implemented. Comparing with other state-of-the-art segmentation variational models, the most striking result to emerge from the data is that the proposed method has higher segmentation performance. Benefiting from appropriate point landmarks, the proposed segmentation method can tackle noisy, weak edges and corrupted area images effectively and robustly.     

基于Mumford-Shah模型的参数估计和两阶段图像分割方法

Mumford-Shah两相分片常数模型是一个有效的图像分割模型,但当模型用于带有噪声的图像时,其水平集解法存在对初始解和长度参数敏感这两个问题.文中给出一种两阶段分割方法,首先利用传统的简单分割方法获得一个粗分割,再将其作为变分模型的初始解,从而实现自动选取初始解.文中还给出一个有效的自适应长度参数估计模型,该模型依据图像中噪声方差大小来确定参数.两阶段分割方法和自适应参数估计结合起来使得算法大大减弱了对参量的敏感性,而且可以正确、快速地分割.针对一些计算机生成图像和实际图像的实验结果验证了算法是有效的.     

Active contours driven by local Gaussian distribution fitting energy

This paper presents a new region-based active contour model in a variational level set formulation for image segmentation. In our model, the local image intensities are described by Gaussian distributions with different means and variances. We define a local Gaussian distribution fitting energy with a level set function and local means and variances as variables. The energy minimization is achieved by an interleaved level set evolution and estimation of local intensity means and variances in an iterative process. The means and variances of local intensities are considered as spatially varying functions to handle intensity inhomogeneities and noise of spatially varying strength (e.g. multiplicative noise). In addition, our model is able to distinguish regions with similar intensity means but different variances. This is demonstrated by applying our method on noisy and texture images in which the texture patterns of different regions can be distinguished from the local intensity variance. Comparative experiments show the advantages of the proposed method.     

Active contours driven by weighted region-scalable fitting energy based on local entropy

In this paper, we present a scheme of improvement on the region-scalable fitting (RSF) model proposed by Li et al. (Minimization of region-scalable fitting energy for image segmentation, IEEE Transactions on Image Processing 17(10) (2008) 1940-1949) in terms of robustness to initialization and noise. First, the Gaussian kernel for the RSF energy is replaced with a “mollifying” kernel with compact support. Second, the RSF energy is redefined as a weighted energy integral, where the weight is local entropy deriving from a grey level distribution of image. The total energy functional is then incorporated into a variational level set formulation with two extra internal energy terms. The new RSF model not only handles better intensity inhomogeneity, but also allows for more flexible initialization and more robustness to noise compared to the original RSF model.     

Simultaneous vector-valued image segmentation and intensity nonuniformity correction using variational level set combined with Markov random field modeling

Object quantification requires an image segmentation to make measurements about size, material composition and morphology of the object. In vector-valued or multispectral images, each image channel has its signal characteristics and provides special information that may improve the results of image segmentation method. This paper presents a region-based active contour model for vector-valued image segmentation with a variational level set formulation. In this model, the local image intensities are characterized using Gaussian distributions with different means and variances. Furthermore, by utilizing Markov random field, the spatial correlation between neighboring pixels and voxels is modeled. With incorporation of intensity nonuniformity model, our method is able to deal with brain tissue segmentation from multispectral magnetic resonance (MR) images. Our experiments on synthetic images and multispectral cerebral MR images with different noise and bias level show the advantages of the proposed method.     

基于Level Set方法的图像分割

研究了基于水平集的图像分割,提出了一种无需重新初始化,基于边缘信息的变分水平集图像分割算法.该算法消除了影响水平集计算量的重新初始化步骤,加速了轮廓线的演化,提高了算法的鲁棒性,同时使得初始化方法更加灵活.     

图像分割中局部能量驱动的快速主动轮廓模型

为了解决图像对象灰度分布不一致性的分割难题,提高图像分割速度,提出了一个全新的快速主动轮廓模型。它由曲线周围局部的统计信息驱动曲线发生形变演化,并使用图像中的边缘信息来引导曲线的演化方向。模型中,根据区域模板与演化曲线共同定义的局部统计信息创建数据拟合项,并应用水平集方法求解曲线的演化。对合成图像和医学图像的实验结果表明,本文提出的分割模型可以同时分割多个灰度不一致的对象,分割速度快,结果稳定,对噪声具有很好的鲁棒性。     

基于LBM对流扩散方程的水平集图像分割方法

为使图像处理更快速稳定,文中通过研究偏微分方程的元胞自动机模型,提出了一种基于格子波尔兹曼模型（LBM）对流扩散方程的图像分割算法：用对流扩散方程替换水平集方程,利用LBM求解对流扩散方程,实现基于LBM的水平集图像分割。实验分析表明,该方法能精确求解对流扩散方程,算法模型能够取得闭合的分割曲线,同样能够很好的处理图像拓扑结构的变化。并且通过与水平集方法和窄带水平集方法进行计算速度实验对比,可证明该算法大大减少了分割的计算量。