一种基于广义梯度矢量流Snake模型的心脏MR图像分割方法

提出了一种基于广义梯度矢量流Snake模型的心脏核磁共振图像左心室内、外膜分割方法。首先构造了一种基于目标边缘的方向广义梯度矢量流(edge-based directional generalized gradient vector flow, EDGGVF) Snake模型,该模型在传统GGVF的基础上,结合目标边缘图梯度方向信息,将左心室内、外膜区分为正边缘和负边缘,从而实现左心室内外膜的全自动分割。其次,根据左心室近似为圆形的形状特点,引入了圆形能量约束,有利于克服由于图像灰度不均、乳突肌等引起的局部极小。实验结果表明,该方法可以高效准确地自动分割出左心室内、外膜。     

一种新的心脏核磁共振图像分割方法

心脏核磁共振图像分割一直是医学影像分析领域的研究热点和难点,文中提出了一种基于梯度矢量流Snake模型的左心室分割方法.作为对梯度矢量流(GVF)的改进,提出了退化最小曲面梯度矢量流(dmsGVF).该模型对弱边界泄漏有更好的鲁棒性;挖掘了左心室的形状特点,采用相应的形状约束,克服了由于图像灰度不均而导致的局部极小,也大大减弱了分割结果对初始轮廓的依赖;对于左室壁外膜的分割,挖掘了左室壁内、外膜的位置关系,通过重新组合梯度分量来构造新的外力场.这种外力场能够克服原始梯度矢量流的不足,使得室壁外膜边缘很弱时也能得到保持,以左室壁内膜分割结果作为初始化能够自动地分割出左室壁外膜.实验结果表明,该方法能高效准确地同时分割左室壁内、外膜.     

基于各向异性扩散活动轮廓模型的左心室MRI分割

结合各向异性扩散算法与梯度矢量流活动轮廓模型,提出了基于各向异性扩散活动轮廓模型并应用于心脏核磁共振图像分割;模型采用各向异性扩散方程构造活动轮廓模型的外部能量函数,得到边界更加清晰的分段平滑图像,运用梯度矢量流将边缘图梯度散射到平坦区域,可以有效抑制噪声,同时保持了目标边界;对左心室核磁共振图像的分割实验表明,该模型可以克服噪声和伪影的干扰,与原梯度矢量流模型相比具有更高的精确性和可靠性,有利于实现自动分割.     

一种心脏核磁共振图像左室壁内、外膜分割方法

为了充分利用心脏核磁共振图像(magnetic resonance image,简称MRI)中关于左心室的解剖和功能信息,必须先分割左室壁内、外膜.提出一种基于Snake模型的左室壁内、外膜分割方法.首先提出了Snake模型的卷积虚拟静电场外力模型CONVEF(convolutional virtual electric field),该外力场捕捉范围大、抗噪能力强、在C形凹陷区域等问题上性能突出,而且基于卷积运算,采用快速Fourier变换可以实时计算.就左室壁内膜的分割而言,考虑到左室壁的形状近似为圆形,引入基于圆形约束的能量项.对于左室壁外膜的分割,充分挖掘了左室壁内、外膜形状上的相似性和位置上的相关性,构造了形状相似性内能和一个新的边缘图,该边缘图用来计算新的外力场.基于所有这些策略并采用内膜的分割结果初始化,可以自动、准确地分割外膜.通过对一套活体心脏MR(magnetic resonance)图像进行分割并和手工分割结果和GGVF(generalized gradient vector flow) Snake模型的分割结果进行比较,结果表明该方法是有效的.     

Locating object contours in complex background using improved snakes

An active contour model, called snake, can adapt to object boundary in an image. A snake is defined as an energy minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines or edges. The traditional snake model fails to locate object contours that appear in complex background. In this paper, we present an improved snake model associated with new regional similarity energy and a gravitation force field to attract the snake approaching the object contours efficiently. Experiment results show that our snake model works successfully for convex and concave objects in a variety of complex backgrounds.     

Video object tracking based on improved gradient vector flow snake and intra-frame centroids tracking method

Accurately tracking the video object in video sequence is a crucial stage for video object processing which has wide applications in different fields. In this paper, a novel video object tracking algorithm based on the improved gradient vector flow (GVF) snake model and intra-frame centroids tracking algorithm is proposed. Unlike traditional gradient vector flow snake, the improved gradient vector flow snake adopts anisotropic diffusion and a four directions edge operator to solve the blurry boundary and edge shifting problem. Then the improved gradient vector flow snake is employed to extract the object contour in each frame of the video sequence. To set the initial contour of the gradient vector flow snake automatically, we design an intra-frame centroids tracking algorithm. Splitting the original video sequence into segments, for each segment, the initial contours of first two frames are set by change detection based on t-distribution significance test. Then, utilizing the redundancy between the consecutive frames, the subsequent frames’ initial contours are obtained by intra-frame motion vectors. Experimental results with several test video sequences indicate the validity and accuracy of the video object tracking.     

Segmentation of cardiac tagged MR images using a snake model based on hybrid gradient vector flow

In the segmentation of cardiac tagging magnetic resonance (tMR) images, it is difficult to segment the left ventricle automatically by using the traditional segmentation model because of the interference caused by the tags. A new snake model based on hybrid gradient vector flow (HGVF) is proposed by us to improve this segmentation. Due to the different characteristics between endocardium and epicardium of the left ventricle (LV), several gradient vector flows (GVFs) with distinctive boundary information would be fused to segment these two sub regions individually. For segmentation of endocardium, we construct a new HGVF in snake model fused by three independent GVFs. These flows are respectively exported from the original cardiac tMR image, the tags-removed image and the local-filtered image. On the other hand, since the epicardium is with a nearly-circle shape, we construct the other HGVF which is composed of two different GVFs. One of them is derived from the tags-removed image either and the other one is derived from the ideal circle-shape image. Some experiments have been done to validate our new segmentation model. The average overlap of the endocardium segmentation is 89.67% (its mean absolute distance is 1.86 pixels), and the average overlap of the epicardium segmentation is 95.88% (its mean absolute distance is 1.64 pixels). Experimental results show that the proposed method improves the segmentation performance compared to some available methods effectively.     

基于Perona-Malik模型的各向异性主动轮廓外力场

利用经典的Perona-Malik各向异性去噪模型具有保护图像边界信息的特点，将经过Perona-Malik模型处理后图像的负梯度作为外力场，研究其对主动轮廓法分割结果的影响，提出了一种主动轮廓外力场模型PMF。理论分析和实验结果表明，PMF模型不仅能够保持图像的边界信息，克服了传统外力场不能进入图像凹部的缺陷，而且对初始曲线的约束较少。由于PMF是基于去噪模型而得，因此具有较好的鲁棒性。     

基于GVF和压力Snake模型的哑铃型目标提取

针对传统活动模型初始化曲线严格的位置选择问题和梯度矢量流场模型存在的哑铃型目标"临界点"问题,提出了梯度矢量流场构造出气球压力的活动轮廓改进模型.利用了梯度矢量流场决定形变点的压力方向,在该构造压力与图像外力及轮廓曲线内力的共同作用下模型完成目标提取.结合实例对改进模型和算法进行了试验分析,结果表明了模型的可行性和算法的有效性.     

An object class-uncertainty induced adaptive force and its application to a new hybrid snake

Object segmentation is of paramount interest in many imaging applications, especially, those involving numeric, symbolic, syntactic, or even high level cognitive knowledge perception. Among others, “snake”—an “active contour” model—is a popular boundary-based segmentation approach where a smooth curve is continuously deformed to lock onto an object boundary. The dynamics of a snake is governed by different internal and external forces. A major limitation of the present framework has been the difficulty of incorporating object-intensity driven features into snake dynamics so as to prevent uncontrolled expansion/contraction once the snake leaks through a weak boundary region. In this paper, a local-intensity-driven “adaptive force” is introduced into the model using object class-uncertainty theory. Given a priori knowledge of object/background intensity distributions, class-uncertainty theory yields object/background classification of every location and establishes its confidence level. It has been demonstrated earlier that confidence level is high inside homogeneous regions and low near boundaries. In the current paper, object class-uncertainty theory has been applied to control snake deformation leading to a new adaptive force acting outward (expanding) inside intensity-defined object regions and inward (squeezing) inside background regions. It has been demonstrated that the method possesses potential to resist uncontrolled expansion of a snake contour (for an expanding type) inside background after leaking through a weak boundary. Further, it has been shown that the adaptive force operates in a complementary fashion with the image intensity gradient by reducing its strength near boundaries using the confidence level of classification. Another major contribution of this paper is the formulation of a “hybrid snake” (HS)—a new model, where an initial contour is gradually deformed over a hybrid energy surface composed of some direct energies (e.g., internal energies) and other indirect energies contributed by local contour displacements over a force-field (e.g., image or user-constrained force-field). Applications of the proposed adaptive force-enabled HS on different phantom and real images have been presented and comparisons have been made with a conventional snake (CS). Finally, a quantitative comparison based on computer-generated phantoms at various levels of blur and noise has been provided.     

基于改进自仿射映射系统与参数活动轮廓的医学图像分割算法

Snake模型分割图像时要求初始化轮廓线位于目标图像特征附近,且处理弱边界与深度凹陷区域的能力较弱,对此提出一种基于改进自仿射映射系统与参数活动轮廓的医学图像分割算法。首先,使用高斯滤波器对给定图像进行平滑处理并计算其小波系数;然后,在每个小波尺度的子矩阵中定义一些自仿射映射;之后,将不同小波尺度对应的子力叠加以获得自仿射力;最终,基于动态力公式引导snake模型变形。基于医学图像的仿真实验结果表明,本算法对于医学图像的分割性能较好,有效地提高了snake模型对弱边界与深度凹陷区域的处理能力。     

基于改进的snake模型的嘴唇轮廓提取

为了更好地利用snake模型来提取彩色图像中的物体轮廓,提出一种改进的snake算法。此方法首先自动生成snake的初始模型,然后在GVF-snake的基础上重新设计了snake的外部能量函数,采用色彩聚类算法对原始图像进行分割,利用像素到聚类中心的距离增强图像并进行差分运算,提取有意义区域的边缘梯度,对GVF向量场进行了归一化处理并改进了平滑因子。实验结果证明,改进后的算法,特别是在处理彩色图像时,大大优于原始方法,提高了轮廓提取的精度且有较好的鲁棒性。     

基于力场分析的主动轮廓模型

传统Snake模型存在的缺点是，其初始轮廓必须靠近图像中感兴趣目标的真实边缘，否则会得到错误结果，且由于Snake模型的非凸性，结果不能进入感兴趣目标的深凹部分，很容易陷入局部极小点，由此该文提出一种基于力场分析的主动轮廓模型，详细分析了基于欧氏距离变换的距离势能力场分布，归纳出感兴趣目标上真轮廓点与假轮廓点的判别标准，建立了由曲线能量到最终结果的有效方法，避免了Snake陷入局部极小点，实验结果表明，该模型具有较大的捕获区域，能够进入感兴趣目标的深凹部分，准确提取感兴趣目标的轮廓，与GVF Snake模型相比，该模型具有很小的计算量。     

Automatical detection of face features and exact face contour

The approach based on the mathematical morphology and the variational calculus is presented for the detection of an exact face contour in still grayscale images. The facial features (eyes and lips) are detected by using the mathematical morphology and the heuristic rules. Using these features an image is filtered and an edge map is prepared. The face contour is detected by minimizing its internal and external energy. The internal energy is defined by the contour tension and the rigidity. The external energy is defined by using the generalized gradient vector flow field of the image edge map. Initial contour is calculated using the detected face features. The contour detection experiments were performed using the database of 427 face images. Automatically detected contours were compared with manually labeled contours using an area and the Euclidean distance-based error measures.     

分水岭算法应用于主动轮廓模型能量分割算法的研究

主动轮廓模型(snake模型)被广泛应用于边缘提取、图像分割等领域。该模型能对目标适当初始化,并进行自主收敛,使得能量处于极小值状态,以达到目标分离的效果。当目标初始位置敏感时,需要依赖其他机制对内部能量进行合理初始化,由于模型的非凸性,它有可能收敛到局部极值点甚至发散。将分水岭算法应用于主动轮廓模型的能量分割算法,通过改进的分水岭算法确定主动轮廓模型的初始轮廓,利用迭代完成对轮廓点周围的局部近邻点的检索,以选取更小的轮廓模型,当获得最小值时完成目标轮廓的提取。     

基于改进Snake模型的超声乳腺肿瘤轮廓提取

二维超声影像中肿瘤轮廓特征是判断乳腺肿瘤的良恶性的重要依据。针对超声医学图像的特点,本研究对经典的Snake模型进行了改进:内部能量中加入轮廓平均长度项的控制;外部能量由基于图像统计特征的区域能量以及梯度方向势能决定,并提出了基于贪婪算法求解模型最小值的快速算法。实验结果显示本算法在噪声强度较大的模拟图像和超声医学图像中均取得了同人工分割近似的结果,而经典的Snake模型和GVF模型受噪声干扰较大。大量的实验证明本算法有效地克服了散斑噪声对分割结果的影响,可准确高效地提取超声图像中的乳腺肿瘤轮廓。     

具有曲线形结构的物体边界和骨架的提取

用各向同性扩散得到梯度矢量流场的能量,并获得初始边界和骨架点（无须任何初始化）;最后利用蛇模型演化这些初始点,当模型能量达到最小时演化停止.最终的点即为所需要的边界和骨架.该方法能同时得到物体的边界和骨架,改进了曲线结构强度图的计算,减少了计算量.采用人工图像和实际图像验证了该方法的有效性.     

一种改进的活动轮廓图像分割技术

图像分割是由图像处理到图像分析的关键步骤，也是一种基本的计算机视觉技术。针对传统的活动轮廓外力模型均存在一些难以克服的缺点，提出了一种改进的活动轮廓图像分割技术，并首先介绍了用活动轮廓进行目标分割的基本原理，即一条曲线在其内部能量和外部能量的共同作用下，可以移动到所期望的位置，并且当曲线到达目标位置的时候，活动曲线所具有的能量达到最小。在传统的活动轮廓中，外部能量通常由目标点的梯度势能场给出，但是由于梯度势能场存在着一些难以克服的缺点，即不能够很好地指导曲线的移动，为此，对其进行了改进，即采用一种梯度向量流场作为外部能量场的方法，从而有效地克服了传统梯度势能场捕捉范围小以及难以处理凹平面的缺点，并通过实验证明了该方法的有效性。     

一种新的基于snake模型的水平集图像分割方法

介绍了一种新的变分函数来替代传统水平集方法中的符号距离函数,因而可以完全忽略重复初始化符号距离函数的步骤,提高了计算效率。用一个能量函数来表示基于snake模型水平集函数的变化情况。其中能量函数主要由内部能量和外部能量表示。利用内部能量描述曲线的张力和平滑性;外部能量则基于图像数据,并在图像的目标边界形成极小值。同时最小化内部和外部能量,产生内力和外力：内力控制曲线演化的方向,并保持曲线不被过度弯曲;外力则吸引曲线到达目标边缘。     

Adaptive diffusion flow active contours for image segmentation

Gradient vector flow (GVF) active contour model shows good performance at concavity convergence and initialization insensitivity, yet it is susceptible to weak edges as well as deep and narrow concavity. This paper proposes a novel external force, called adaptive diffusion flow (ADF), with adaptive diffusion strategies according to the characteristics of an image region in the parametric active contour model framework for image segmentation. We exploit a harmonic hypersurface minimal functional to substitute smoothness energy term in GVF for alleviating the possible leakage. We make use of the p(x) harmonic maps, in which p(x) ranges from 1 to 2, such that the diffusion process of the flow field can be adjusted adaptively according to image characteristics. We also incorporate an infinity laplacian functional to ADF active contour model to drive the active contours onto deep and narrow concave regions of objects. The experimental results demonstrate that ADF active contour model possesses several good properties, including noise robustness, weak edge preserving and concavity convergence.