一种基于偏微分方程的图像分割算法

针对几何活动轮廓模型（GAC模型）在基于偏微分方程的图像分割领域中,算法复杂,计算量大导致演化时间长,演化速度在边界上通常不为零,引起演化曲线进入到目标的内部;或是当图像的对象有较深的凹陷边界时,曲线停在某一局部极小值状态,并不与对象的边界相一致等问题。本文提出了一种基于偏微分方程的图像分割算法,通过对停止速度场进行多尺度张量扩散,然后运用GACA模型进行分割。实验证明：本算法在不降低射线图像分割质量的前提下,可使演化时间比传统的GAC模型演化时间减少65%左右,还在一定程度上减少了边界泄露问题。     

利用模糊特征改进Snakes模型的图像分割

利用模糊特征自适应地控制曲线法向力场改进参数主动轮廓模型,改进后的模型可以对弱边缘、无边缘区域和纹理图像进行分割。曲线法向力场加速了曲线收敛到目标区域边界,改进了抓取范围和提取凹区域的能力。对弱边缘图像、医学图像和纹理的分割实验表明,新方法具有良好的性能。     

基于变化检测和改进的GVF snake模型的运动目标轮廓提取

为了解决当前目标跟踪中目标轮廓提取不精确的问 题,在对传统GVF (gradient vector flow)snake活动轮廓模型改进的基础上,提 出一种基于变化检测和改进的GVF snake活动轮廓模型的视频目标轮廓提取算法。首先,通 过 基于t显著性检验的变化检测方 法消除背景边界的影响,并获取初始运动变化区域的临界四边形作为GVF snake的初始轮廓 。然后,对初始轮廓应用改进 的GVF snake模型以获得精确的轮廓边界。改进模型采用4方向各项异性扩散,并采用下降速 度较快的保真项系数以增强 GVF snake进入凹陷的能力,且保持对弱边界的收敛。本文方法克服了手动绘制初始轮廓的 缺点,对传统GVF snake方法进 行了改进,且空间准确度(SA)有很大提高。实验表明 ,本文方法成功分割出目标凹陷部分并对弱边界有较好的收敛效果,提高了轮廓提取的精确 度。     

基于Snake模型的复杂区域图像分割

在复杂区域图像分割中,针对传统Snake模型不能收敛到深凹陷区域等缺点,从内部能量函数和算法实现两方面入手对传统Snake模型进行改进,增加了一项由力作功产生的能量项,并采用Greey算法分两阶段实现.结果表明,改进的Snake模型能迅速地收敛到深凹陷区域和更复杂区域,且减弱了分割结果对初值的依赖性和噪声点对边界的影响.     

一种基于参数活动轮廓模型的高能闪光照相图像分割算法

针对高能闪光照相系统成像质量较差的特点,提出了一种基于参数活动轮廓模型(Snake模型)的闪光照相图像分割算法.该算法在传统高斯力Snake模型中引入包含图像区域信息的变力,以目标和背景两区域具有最小方差为准则,构建兼顾边缘和区域信息的外部能量函数.数值实验结果表明,该算法对初始轮廓位置不敏感,较好地解决了客体凹陷区域分割问题,能够实现对含噪声的弱边界闪光图像的自动分割.     

基于GVF Snake模型的设备内壁图像轮廓提取

主动轮廓模型主要用于计算机视觉与图像处理,尤其是用于检测对象的边界,是目前流行的图像分割算法,其主要优点是无论图像的质量如何,总可以抽取得到光滑、封闭的边界.通过使用梯度矢量流(Gradient Vector Flow,GVF)主动轮廓模型对设备内壁图像进行分割,克服了传统主动轮廓模型不能检测目标凹陷处,初始轮廓必须靠近物体边缘,以及收敛速度较慢的缺点.实验结果表明该算法不仅可以获得较好的设备内壁图像分割效果,而且能提高轮廓提取的速度,为标定设备内壁有损部位的几何参数提供良好的环境.     

一种改进的分裂合并图像分割算法

图像分割是图像分析和目标识别中的关键技术之一。在传统图像分割方法的基础上,提出一种将改进的自适应遗传算法与合并分裂法相结合的图像分割算法。针对遗传算法运算速度低,容易陷入局部最优值、早熟收敛等缺点,在此通过对遗传操作算子的改进、适应度评价函数的科学设计以及交叉和变异概率的自适应调整来降低图像分割产生的误差。计算机仿真结果证明,该算法能够取得较好的图像分割效果。     

一种血管约束的局部活动轮廓模型

活动轮廓作为一种重要的图像分割工具,近几年来在理论和应用方面都有很大的发展。然而,现有轮廓模型在处理灰度均匀性较差的图像时,通常存在较高的分割误差,并且对初始轮廓曲线位置敏感。为此,本文提出一种基于血管特征约束的活动轮廓模型,该模型首先使用局部相位（Local Phase）的血管增强算法对图像进行增强处理以生成一种不同于图像灰度的血管特征信息,然后将血管信息和图像灰度以线性加权的形式引入到局部二值拟合（Local Binary Fitting,LBF）能量泛函中,指导图像血管分割。基于视网膜血管图像数据（Digital Retinal Images for Vessel Extraction,DRIV）的实验显示：该模型能成功地从灰度分布不均匀和弱边界轮廓的视网膜图像中提取血管,分割灵敏度和准确性分别达到74.43%和93.67%,同时对初始轮廓曲线位置的敏感性大为降低。由上述可知,该模型具有高分割准确性和低初始位置敏感性。     

基于主动轮廓模型的红外图像轮廓提取算法

针对主动轮廓模型存在的对初始轮廓位置敏感、凹性目标轮廓无法正确收敛等问题,本文将自适应边缘检测和主动轮廓模型相融合,提出一种改进的红外图像目标轮廓自动提取算法。首先,采用最大类间方差法计算红外图像边缘检测算法的自适应阈值,获取目标初次边缘,降低对初始轮廓位置的敏感性;对初次边缘分别进行横向与纵向填充,填充图像相与运算,对得到目标区域提取二次边缘,将其作为主动轮廓模型的初始轮廓,保证目标凹陷区域轮廓的有效收敛。最后,通过仿真分析验证了该方法能够实现红外目标轮廓的精确自动收敛。     

基于自适应多尺度与轮廓梯度的遥感图像分割网络

遥感图像分割算法易受环境因素干扰，如物体遮挡、光照不均匀等。现有的深度学习遥感图像语义分割方法通常采取端到端的编解码结构，但针对相似度较高物体的结构和轮廓，仍存在分割不准确的问题。为了提高算法鲁棒性、分类准确率，提出一种基于轮廓梯度学习的深度卷积神经网络遥感图像语义分割算法。为了提高预测特征图的质量，首先基于SegNet模型，提出自适应注意力的多通道多尺度特征融合网络（D-MMA Net），其中D-MA block采用基于注意力的自适应多尺度模块，根据学习到的权重自适应地对不同尺度特征进行提取，以获得更多有效的高级语义特征。为进一步细化提取物体的边界，基于Sobel边缘检测算子原理提出可学习的轮廓提取模块。最后将轮廓信息与多尺度语义特征相结合，以增强对图像空间分辨率的鲁棒性。实验结果表明，所提算法提高分割的准确率，对于不规则物体边界，能有良好的分割效果。     

结合边界和区域的水平集超声图像分割算法

针对距离正则化的水平集演化（DRLSE）模型难以处理弱边缘图像、初始轮廓敏感以及曲线演化方向单一等问题,提出一种结合边缘和区域信息的变分水平集超声图像分割模型。该模型采用改进的四阶偏微分方程进行滤波,实现在去除噪声的同时保护图像边缘信息;构造了自适应加权系数,实现曲线自适应地向内或者向外演化;引入CV模型的外部能量项,将图像的边缘信息和区域信息相结合,提高了全局分割能力。实验结果表明：该方法在分割超声图像时,具有演化结果稳定,边缘定位准确的特点,可以较好地提取超声图像中的目标。     

图像分割中采用自适应3次B样条修饰轮廓线

提出了一种在图像分割中获得连续光滑轮廓线的方法,该方法先以动态京都科像的全局最小累积代价阵,并从累积代价梯度降低最快的方向提取全局最优的轮廓线,然后用一种自适应3次B样条对获得的线进行修饰和平滑处理。该样条可根据轮廓线不同处的曲率变化情况,自适应地调整控制点的分布,在各类图像上的试验表明,该方法能有效地消除轮廓线上的小锯齿,获得较其它方法更平滑的曲线,同时又保留了轮廓线的特征细节。     

基于局部图划分的多相活动轮廓图像分割模型

几何活动轮廓模型是图像分割领域的强有力工具。最近,一种基于成对相似性的图划分活动轮廓(GPAC)模型被提出,并有效应用于均质图像分割。但是,该模型的连接权函数仅与图像光谱相关,使得模型在低对比度模糊图像的应用存在较大局限,同时,成对相似性的计算量大,模型的数值实现效率不甚理想。针对这些问题,该文引入测地核函数定义连接权函数,结合多相水平集,提出了基于局部图划分的多相活动轮廓图像分割模型。自然图像的实验结果证明了该模型的有效性。     

Adaptive methods for dithering color images

Most color image printing and display devices do not have the capability of reproducing true color images. A common remedy is the use of dithering techniques that take advantage of the lower sensitivity of the eye to spatial resolution and exchange higher color resolution with lower spatial resolution. An adaptive error diffusion method for color images is presented. The error diffusion filter coefficients are updated by a normalized least mean square-type (LMS-type) algorithm to prevent textural contours, color impulses, and color shifts, which are among the most common side effects of the standard dithering algorithms. Another novelty of the new method is its vector character: previous applications of error diffusion have treated the individual color components of an image separately. We develop a general vector approach and demonstrate through simulation studies that superior results are achieved.     

A fuzzy energy-based active contour model with adaptive contrast constraint for local segmentation

Image segmentation is to divide an image into different parts or extract some interested objects. Active contour model and fuzzy clustering are two widely used segmentation methods, which have been integrated into an effective model in recent years. Local segmentation is often needful in medical image processing. In view of local segmentation on inhomogeneous images, a new average fuzzy energy-based active contour model is proposed in this paper, in which the total fuzzy energy integrates the approximate weighted average and arithmetic average variances of the image. And an adaptive contrast constraint condition is introduced to prevent the curve from falling into local minimum, which further improves the robustness of the segmentation model to initial contour. Experimental results on synthetic and medical images demonstrate that the proposed model has considerable improvements in terms of segmentation accuracy and robustness compared to several existing local segmentation models.     

基于图像分解的稀疏正则化多区域图像分割方法

针对图像具有不同特征的成分,提出一种基于图像分解的多区域图像分割模型和算法.首先将图像分解项引入到图像分割模型中,递减了纹理和噪声对分割的影响;其次使用稀疏正则化方法保持分割区域的边缘几何结构;最后基于增广Lagrange乘子法,给出一种由扩散流引导的小波迭代阈值图像分割算法.一系列实验结果表明,提出的方法抗干扰能力强,对噪声具有更好的鲁棒性.提出的方法不仅能够分割结构图像,并且能够分割较复杂的纹理图像.     

Integrated active contours for texture segmentation.

We address the issue of textured image segmentation in the context of the Gabor feature space of images. Gabor filters tuned to a set of orientations, scales and frequencies are applied to the images to create the Gabor feature space. A two-dimensional Riemannian manifold of local features is extracted via the Beltrami framework. The metric of this surface provides a good indicator of texture changes and is used, therefore, in a Beltrami-based diffusion mechanism and in a geodesic active contours algorithm for texture segmentation. The performance of the proposed algorithm is compared with that of the edgeless active contours algorithm applied for texture segmentation. Moreover, an integrated approach, extending the geodesic and edgeless active contours approaches to texture segmentation, is presented. We show that combining boundary and region information yields more robust and accurate texture segmentation results.     

Image segmentation and selective smoothing by using Mumford-Shah model.

Recently, Chan and Vese developed an active contour model for image segmentation and smoothing by using piecewise constant and smooth representation of an image. Tsai et al. also independently developed a segmentation and smoothing method similar to the Chan and Vese piecewise smooth approach. These models are active contours based on the Mumford-Shah variational approach and the level-set method. In this paper, we develop a new hierarchical method which has many advantages compared to the Chan and Vese multiphase active contour models. First, unlike previous works, the curve evolution partial differential equations (PDEs) for different level-set functions are decoupled. Each curve evolution PDE is the equation of motion of just one level-set function, and different level-set equations of motion are solved in a hierarchy. This decoupling of the motion equations of the level-set functions speeds up the segmentation process significantly. Second, because of the coupling of the curve evolution equations associated with different level-set functions, the initialization of the level sets in Chan and Vese's method is difficult to handle. In fact, different initial conditions may produce completely different results. The hierarchical method proposed in this paper can avoid the problem due to the choice of initial conditions. Third, in this paper, we use the diffusion equation for denoising. This method, therefore, can deal with very noisy images. In general, our method is fast, flexible, not sensitive to the choice of initial conditions, and produces very good results.     

Multi-feature gradient vector flow snakes for adaptive segmentation of the ultrasound images of breast cancer

Segmentation of ultrasound (US) images of breast cancer is one of the most challenging problems of the modern medical image processing. A number of popular codes for US segmentation are based on a generalized gradient vector flow (GGVF) method proposed by Xu and Prince. The GGVF equations include a smoothing term (diffusion) applied to regions of small gradients of the edge map and a stopping term to fix and extend large gradients appearing at the boundary of the object.The paper proposes two new directions. The first component is diffusion as a polynomial function of the intensity of the edge map. The second component is the orientation score of the vector field. The new features are integrated into the GGVF equations in the smoothing and the stopping term.The algorithms, having been tested by a set of ground truth images, show that the proposed techniques lead to a better convergence and better segmentation accuracy with the reference to conventional GGVF snakes. The adaptive multi-feature snake does not require any hand-tuning. However, it is as efficient as the standard GGVF with the parameters selected by the “brutal force approach”. Finally, proposed approach has been tested against recent modifications of GGVF, i.e. the Poisson gradient vector flow, the mixed noise vector flow and the convolution vector flow. The numerical tests employing 195 synthetic and 48 real ultrasound images show a tangible improvement in the accuracy of segmentation.