Morphological multiscale decomposition of connected regions with emphasis on cell clusters

After binarization of cells in complex cytological and histological images the segmented structures can be rather far away from a final quantification of features of single cells since cells may overlap and cluster strongly. Separating optically, partially or totally fused entities like cells is a problem which frequently cannot be solved by a watershed segmentation or a basic morphological processing of images. However, considering different morphological scales after iterative erosion gives rise to dominant markers of singular objects. Performing a reconstruction by iterative dilation yields a scale-independent decomposition of multiple disjointed cell clumps of different sizes within an image.Accordingly we developed a technique that splits cell clumps into meaningful parts. Since this method is based on the analysis of the morphological-scale space, generated by iterative erosion, it is independent on the size of cell clusters. The detection of dominant points within the eroded scales are cell-specific markers. The converse integration of markers at different scales is obtained by a successive reconstruction based on constrained dilation of the original cell shape.The advantages of this approach are the independence of cell shapes which are clumped, the consideration of holes or background intensities within objects and the robustness with regard to convergence. An important benefit is the fitting of the operation time to the size of clusters by the size of the morphological structuring element. This means, that this approach requires only one parameter. Finally, a better match of the morphological scale space approach was found and compared with the ground truth as well as the results of the watershed technique.The primary object of this paper is to highlight the algorithm and its results by using different examples from benchmark databases, self generated images that exhibit different topological features and complex configurations of cells within histological images.     

Iterative Graph Cuts for Image Segmentation with a Nonlinear Statistical Shape Prior

Shape-based regularization has proven to be a useful method for delineating objects within noisy images where one has prior knowledge of the shape of the targeted object. When a collection of possible shapes is available, the specification of a shape prior using kernel density estimation is a natural technique. Unfortunately, energy functionals arising from kernel density estimation are of a form that makes them impossible to directly minimize using efficient optimization algorithms such as graph cuts. Our main contribution is to show how one may recast the energy functional into a form that is minimizable iteratively and efficiently using graph cuts.     

Automatic segmentation of granular objects in images: Combining local density clustering and gradient-barrier watershed

Blob or granular object recognition is an image processing task with a rich application background, ranging from cell/nuclei segmentation in biology to nanoparticle recognition in physics. In this study, we establish a new and comprehensive framework for granular object recognition. Local density clustering and connected component analysis constitute the first stage. To separate overlapping objects, we further propose a modified watershed approach called the gradient-barrier watershed, which better incorporates intensity gradient information into the geometrical watershed framework. We also revise the marker-finding procedure to incorporate a clustering step on all the markers initially found, potentially grouping multiple markers within the same object. The gradient-barrier watershed is then conducted based on those markers, and the intensity gradient in the image directly guides the water flow during the flooding process. We also propose an important scheme for edge detection and fore/background separation called the intensity moment approach. Experimental results for a wide variety of objects in different disciplines – including cell/nuclei images, biological colony images, and nanoparticle images – demonstrate the effectiveness of the proposed framework.     

基于形态学的金相组织图像晶界复原方法

由于金相图像中经常出现晶界模糊、晶界断开等缺陷,针对晶粒形状不规则的特点,成功改进了基于形态学水域生长方法的分割算法.根据粘连晶粒的形态特征,对粘连目标先后采用极限腐蚀、目标编号和反复膨胀的方法求取晶界线以达到分离粘连晶粒,复原图像的目的.实验结果表明,改进的方法对包括晶粒在内的不规则目标具有较好的分割效果,成功解决了晶界问题对后续分析统计工作的干扰.     

Real-time line detection through an improved Hough transform voting scheme

The Hough transform (HT) is a popular tool for line detection due to its robustness to noise and missing data. However, the computational cost associated to its voting scheme has prevented software implementations to achieve real-time performance, except for very small images. Many dedicated hardware designs have been proposed, but such architectures restrict the image sizes they can handle. We present an improved voting scheme for the HT that allows a software implementation to achieve real-time performance even on relatively large images. Our approach operates on clusters of approximately collinear pixels. For each cluster, votes are cast using an oriented elliptical-Gaussian kernel that models the uncertainty associated with the best-fitting line with respect to the corresponding cluster. The proposed approach not only significantly improves the performance of the voting scheme, but also produces a much cleaner voting map and makes the transform more robust to the detection of spurious lines.     

A general shape context framework for object identification

A general shape context framework is proposed for object/image retrieval in occluded and cluttered environment with hundreds of models as the potential matches of an input. The approach is general since it does not require separation of input objects from complex background. It works by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. Its performance degrades gracefully with respect to the amount of structural information that is being occluded or lost. The local neighborhood information applicable to the system can be shape, color, texture feature, etc. Currently, we employ shape information only. The mechanism of voting is based on a novel hyper cube based indexing structure, and driven by dynamic programming. The proposed concepts have been tested on database with thousands of images. Very encouraging results have been obtained.     

基于物理模型的彩色图像分割

本文给出一个基于光学物理模型的真实彩色图像分割算法.算法首先对图像上的颜色变 化(由光照和物体颜色引起)进行分析与综合,然后分割图像.算法的基础是双色反射模型理 论,该理论认为反射光的颜色是界面反射(耀斑颜色)和本体反射(物体颜色)的线性组合,这两 种反射光在颜色空间的三维直方图中形成特定的聚类(点簇).因此分析聚类的性质可帮助确 定光照和物体的颜色,但是有意义的聚类的生成又以图像中物体区域的确定为前提.算法按 照假设检验的策略,依据图像中的连通性和颜色空间中聚类的特征,完成彩色图像的分割,并 产生对景物中所发生的光学过程的物理描述.该描述包括本征反射图像、分割图像、物体和光 照颜色的符号描述.本征反射图像包括只反映界面反射的耀斑图像和从原图像中去除耀斑影 响后的本体图像.     

Fuzzy clustering with learnable cluster-dependent kernels

We propose a new relational clustering approach, called Fuzzy clustering with Learnable Cluster-dependent Kernels (FLeCK), that learns the underlying cluster-dependent dissimilarity measure while seeking compact clusters. The learned dissimilarity is based on a Gaussian kernel function with cluster-dependent parameters. Each cluster’s parameter learned by FLeCK reflects the relative intra-cluster and inter-cluster characteristics. These parameters are learned by optimizing both the intra-cluster and the inter-cluster distances. This optimization is achieved iteratively by dynamically updating the partition and the local kernel. This makes the kernel learning task takes advantages of the available unlabeled data and reciprocally, the categorization task takes advantages of the learned local kernels. Another key advantage of FLeCK is that it is formulated to work on relational data. This makes it applicable to data where objects cannot be represented by vectors or when clusters of similar objects cannot be represented efficiently by a single prototype. Using synthetic and real data sets, we show that FLeCK learns meaningful parameters and outperforms several other algorithms. In particular, we show that when data include clusters with various inter- and intra-cluster distances, learning cluster-dependent parameters is crucial in obtaining a good partition.     

目标自适应图像分块与小目标提取

针对传统二维直方图方法的难点,提出了采用基于分水岭变换的图像自适应分块的解决方法,新方法能使得每个小目标都被分割在同一个图像区域内,克服了传统图像分块方法采用固定分块,易造成将同一目标分到多个区域的缺点。方法中首先采用了基于标记点的灰度图像重建方法对图像进行预处理,在自适应增强目标的同时也克服了分水岭变换易造成过度分割的影响,在此基础上进一步地对图像采取了基于分水岭变换的图像分块,接着在每一个分块区域中采用引入目标分布信息阈值选取方法,得到二值化的结果。实验表明该方法目标分割结果稳定,适合于小目标的分割提取。     

基于top-hat变换与形状特征的蛋白点检测

针对凝胶图像中蛋白质点检测存在弱蛋白质点漏检和重叠蛋白质点难分离的问题,提出了一种基于top-hat变换与形状特征的弱重叠蛋白质点检测算法。采用top-hat变换算法增强弱蛋白质点区域;采用标记控制分水岭法进行粗检测,提取蛋白质点的初始轮廓;根据蛋白质形状特征,自适应设定阈值提取蛋白质点形状标记,并利用提取的标记计算形状距离图;采用基于形状距离的分水岭方法,分离重叠蛋白质点。通过不同类型真实凝胶图像的蛋白质点检测实验,结果表明,该算法具有较高的检测精度和重叠蛋白质点分离率,而且对质量不好的凝胶图像也有较好的检测效果。     

基于超图模型的图像目标识别

基于类属超图模型给出简单图像和复杂图像目标的识别方法。通过提取简单图像的稳健尺度不变特征变换特征,得到其对应的属性图,采用RSOM聚类树的思想和K近邻方法快速实现对简单图像的目标识别。复杂图像存在较大的背景干扰和遮挡的影响,通过滑动窗方法在待识别图像中定位待识别目标区域,并将该区域从待识别图像中分出,然后采用与简单图像识别方法类似的方法完成目标识别,减少背景干扰和遮挡的影响。仿真实验表明,2种图像目标识别方法是有效的。     

一种基于交集的聚类组合算法

聚类作为一种无监督的学习,能根据数据间的相似程度自动地进行分类。提出的基于交集的聚类组合新方法,借鉴了选举投票的思想。给定同一数据集的不同聚类结果,此算法先求出不同聚类结果中每个簇的对应关系,然后计算这几个聚类结果对应簇的交集,对剩余的有争议对象进行投票,最后把投票之后仍未确定归属的对象分配给最近对象所在的簇,或者不经过投票直接将有争议的对象分配给最近对象所在的簇。实验表明,两种方法都能明显改善聚类质量,投票后得到的结果要略优于不投票的结果。     

Finding locally optimum force-closure grasps

This paper presents an iterative procedure to find locally optimum force-closure grasps on 3D objects, with or without friction and with any number of fingers. The object surface is discretized in a cloud of points, so the approach is applicable to objects with any arbitrary shape. The approach finds an initial force-closure grasp that is then iteratively improved through an oriented search procedure. The grasp quality is measured considering the largest perturbation wrench that the grasp can resist with independence of the direction of perturbation. The efficiency of the algorithm is illustrated through numerical examples.     

Reliable Distributed Network Management by Replication

This paper presents a new clustering architecture for SNMP agents that supports semi-active replication of managed objects. A cluster of agents provides fault-tolerant object functionality: replicated managed objects of a crashed agent of a given cluster may be accessed through a peer cluster. The proposed architecture is structured in three layers. The lower layer corresponds to the managed objects at the network elements. The middle layer contains management entities called clusters that monitor and replicate managed objects. The upper layer allows the definition of management clusters as well as the relationship between clusters. A practical tool was implemented and is presented. The impact of replication on network performance is evaluated as well as a probabilistic analysis of replicated object consistency.     

基于轮廓的形状射线描述模型

提出一种新的基于轮廓的形状描述和匹配方法。提取物体的轮廓并在轮廓上进行等间隔采样,利用参考点到采样点的距离、采样点处的轮廓方向及采样点间的空间关系来直观地表达目标的形状特征;通过在不同尺度、方向和位置进行最大表决来获得形状匹配的尺度、旋转和平移不变性;提出了结合局部和整体特征的相似度评分机制来实现目标的匹配和检测。实验表明,形状的射线描述模型不仅能对具有清晰轮廓的目标进行有效的检索和匹配,也可在复杂的图像背景中检测目标。     

On the Decomposition of Cell Clusters

Successful segmentation of a multilevel to a bilevel microscopic cell image rather frequently gives rise to touching objects which need to be separated in order to perform object specific measurements. The standard approach of dealing with this problem is a watershed decomposition of gradient, distance or low pass filtered transforms. However, if cell clustering is excessive, the cell size varies and cells have various shapes that are different from circles the watershed approaches produce unsatisfying results. We found a technique that splits cell clumps into meaningful parts. Since this method is based on the analysis of contour curvature on the scale space of Fourier coefficients relevant dominant points can be recognized. Based on an optimized heuristic approach pairs of these dominant points are recursively matched since splitted objects do not possess concavities respectively intrusions anymore. The advantages of this approach are (i) the independence of cell shapes which are clumped, (ii) the consideration of holes or background intensities within objects, (iii) the robustness in terms of convergence and a few parameters only to adapt to other families of decomposition problems. The objective of this contribution is to explain the algorithm, show its results using different examples from benchmark databases, self generated images and complex configurations of cell images.

基于区间2-型模糊度量的粗糙K-means聚类算法*

现有粗糙K-means聚类算法及系列改进、衍生算法均是从不同角度描述交叉类簇边界区域中的不确定性数据对象,却忽视类簇间规模的不均衡对聚类迭代过程及结果的影响.文中引入区间2-型模糊集的概念度量类簇的边界区域数据对象,提出基于区间2-型模糊度量的粗糙K-means聚类算法.首先根据类簇的数据分布生成边界区域样本对交叉类簇的隶属度区间,体现数据样本的空间分布信息.然后进一步考虑类簇的数据样本规模,在隶属度区间的基础上自适应地调整边界区域的样本对交叉类簇的影响系数.文中算法削弱边界区域对较小规模类簇的中心均值迭代的不利影响,提高聚类精度.在人工数据集及UCI标准数据集的测试分析验证算法的有效性.     

A kernel‐based core growing clustering method

In this paper, a novel clustering method in the kernel space is proposed. It effectively integrates several existing algorithms to become an iterative clustering scheme, which can handle clusters with arbitrary shapes. In our proposed approach, a reasonable initial core for each of the cluster is estimated. This allows us to adopt a cluster growing technique, and the growing cores offer partial hints on the cluster association. Consequently, the methods used for classification, such as support vector machines (SVMs), can be useful in our approach. To obtain initial clusters effectively, the notion of the incomplete Cholesky decomposition is adopted so that the fuzzy c‐means (FCM) can be used to partition the data in a kernel defined‐like space. Then a one‐class and a multiclass soft margin SVMs are adopted to detect the data within the main distributions (the cores) of the clusters and to repartition the data into new clusters iteratively. The structure of the data set is explored by pruning the data in the low‐density region of the clusters. Then data are gradually added back to the main distributions to assure exact cluster boundaries. Unlike the ordinary SVM algorithm, whose performance relies heavily on the kernel parameters given by the user, the parameters are estimated from the data set naturally in our approach. The experimental evaluations on two synthetic data sets and four University of California Irvine real data benchmarks indicate that the proposed algorithms outperform several popular clustering algorithms, such as FCM, support vector clustering (SVC), hierarchical clustering (HC), self‐organizing maps (SOM), and non‐Euclidean norm fuzzy c‐means (NEFCM). © 2009 Wiley Periodicals, Inc.4     

基于数学形态学的灰度图像连接物体分割方法

由于噪声的存在以及连接物体的特点,传统的标记分水岭算法对包含连接物体的灰度图像很难取得满意的分割结果;特别是在背景并不连通的情况下,误分割更为常见;在标记分水岭算法的基础上,提出了一种连接物体分割方法;将属于鲁棒统计的Hough变换用于提取物体标记扩展了标记分水岭算法的应用范围;针对在分割连接物体时,由于背景并非连通,因此允许背景被分别标记,并通过一个后续滤波步骤用以剔除分割后图像中的背景部分,从而得到精确的分割图像;试验证明该算法运算速度快,鲁棒性好,具有广泛的应用价值.     

A multi-prototype clustering algorithm

Clustering is an important unsupervised learning technique widely used to discover the inherent structure of a given data set. Some existing clustering algorithms uses single prototype to represent each cluster, which may not adequately model the clusters of arbitrary shape and size and hence limit the clustering performance on complex data structure. This paper proposes a clustering algorithm to represent one cluster by multiple prototypes. The squared-error clustering is used to produce a number of prototypes to locate the regions of high density because of its low computational cost and yet good performance. A separation measure is proposed to evaluate how well two prototypes are separated. Multiple prototypes with small separations are grouped into a given number of clusters in the agglomerative method. New prototypes are iteratively added to improve the poor cluster separations. As a result, the proposed algorithm can discover the clusters of complex structure with robustness to initial settings. Experimental results on both synthetic and real data sets demonstrate the effectiveness of the proposed clustering algorithm.