结合SVM和香农能量的HSMM心音分割算法

针对基于逻辑回归的隐半马尔可夫模型中希尔伯特（Hilbert）变换提取的心音包络具有较大毛刺,提出一种结合支持向量机（Support vector machine, SVM）和香农能量的隐半马尔可夫模型（Hidden semi-Markov model, HSMM）心音分割算法。首先采用小波降噪的方法对心音进行降噪,接着根据R峰和T波标记心音,提取香农能量包络等特征,然后对结合逻辑回归模型（Logistic regression, LR）的HSMM相关参数进行训练,并借助Viterbi算法推测出最可能的状态。最后,通过SVM模型识别第一心音S₁和第二心音S₂。该算法无需设置硬阈值,有效地抑制了噪声,更有助于包络的提取。实验结果表明,提出的算法分割精确度较参考算法得到显著的提升,具有良好的抗噪性能,取得了更好的分割效果。     

基于混合高斯模型MRF场的CT图像分割

提出了一种基于混合高斯模型的马尔可夫随机场CT图像分割方法.此方法根据工业CT图像的特点,建立混合高斯逼近的图像灰度统计模型;用混合高斯模型作为Markov随机场的先验模型,提出混合高斯Markov随机场分割模型.实验表明,该方法较单高斯模型有很大的改善,对工业CT图像分割效果好.     

基于隐条件随机场的自适应视频分割算法

视频目标分割是视频监视与视频目标跟踪、视频目标识别以及视频编辑的基础. 本文提出了一种基于隐条件随机场 (Hidden conditional random fields, HCRF) 的自适应视频分割算法, 利用 HCRF 模型对视频序列中的时空邻域关系建模. 使用在线学习的方式对相应的参数进行调整, 实现对时空邻域约束关系的权重调整, 提高视频目标分割细节上的效果. 大量的数据测试表明, 与高斯混合模型 (Gaussian mixture model, GMM) 和联合时空的马尔可夫随机场 (Markov random fields, MRF) 等算法相比, 该算法的分割错误率分别降低了23\%和19\%.     

特征一致性约束的视频目标分割

目的 视频目标分割是计算机视觉领域的一个重要方向,已有的一些方法在面对目标形状不规则、帧间运动存在干扰信息和运动速度过快等情况时,显得无能为力。针对以上不足,提出基于特征一致性的分割算法。方法 本文分割算法框架是基于马尔可夫随机场（Markov random field,MRF）的图论方法。使用高斯混合模型,对预先给定的已标记区域分别进行颜色特征的建模,获得分割的数据项。结合颜色、光流方向等多种特征,建立时空平滑项。在此基础之上,加入基于特征一致性的能量约束项,以增强分割结果的外观一致性。这项添加的能量本身属于一种高阶能量约束,会显著增加能量优化的计算复杂度。为此,添加辅助结点,以解决能量的优化问题,从而提高算法速度。结果 在DAVIS_2016（densely annotated video segmentation）数据集上对该算法进行评估与测试,并与最新的基于图论的方法进行对比分析,对比算法主要有HVS（efficient hierarchical graph-based video segmentation）、NLC（video segmentation by non-local consensus voting）、BVS（bilateral space video segmentation）和OFL（video segmentation via object flow）。本文算法的分割结果精度排在第2,比OFL算法略低1.6%;在算法的运行速度方面,本文算法领先于对比方法,尤其是OFL算法的近6倍。结论 所提出的分割算法在MRF框架的基础之上融合了特征一致性的约束,在不增加额外计算复杂度的前提下,提高了分割精度,提升了算法运行速度。     

隐马尔可夫模型中一种新的帧相关建模方法

在使用传统的隐马尔可夫模型（traditional hidden Markov model,简称THMM）刻画现实中的语音时有一个明显的缺点,即THMM不能合适地表征语音信号的时域结构.时域上的相关性被认为对识别非常有用,因为相邻帧间的特征矢量具有很强的相关性.文章提出了一种新的方法,用以把时域的相关性糅合到一个基于传统的隐马尔可夫模型的语音识别系统中.首先,用条件概率的形式处理帧间相关性;然后,用一种非线性的概率近似公式来表征相邻帧之间的相关性.此方法丝毫不增加原来的THMM的空间复杂度,而且也几乎不增     

HMGMRF模型及其在高分辨率影像分割中的应用

通过修改离差预测的方式,对高斯马尔可夫随机场(Gauss Markov Random Field)模型加以改进,提出层次型多光谱高斯马尔可夫随机场 (Hierarchical Multispectral Gauss Markov Random Field,HMGMRF) 模型及其相应的分割算法。影像分割时,先通过HMGMRF模型分析地物在各波段光谱特征的变化趋势（即地物各波段的纹理特征）,期间结合了"谱间相关"这一特性,将离差预测时的邻域空间由原先的单层扩展为多层,增加了纹理特征的维度,从而提高了模型在描述纹理特征方面的能力;接着,基于贝叶斯原理,采用EM (Expectation Maximization)算法对各类地物的模型参数进行迭代估算;最后,基于增强型纹理特征,依据MAP (Maximum A Posteriori)原则,实现影像分割。实验结果表明,所提出的基于HMGMRF模型的分割算法具有较强的识别地物能力,可以获得较高的分割精度。     

融入邻域作用的高斯混合分割模型及简化求解

目的 基于高斯混合模型（GMM）的图像分割方法易受噪声影响,为此采用马尔可夫随机场（MRF）将像素邻域关系引入GMM,提高算法抗噪性。针对融入邻域作用的高斯混合分割模型结构复杂、参数估计困难,难以获得全局最优分割解等问题,提出一种融入邻域作用的高斯混合分割模型及其简化求解方法。方法 首先,构建融入邻域作用的GMM。为了提高GMM的抗噪性,采用MRF建模混合模型权重系数的先验分布。然后,利用贝叶斯理论建立图像分割模型,即品质函数;由于品质函数中参数较多（包括权重系数,均值,协方差）、函数结构复杂,导致参数求解困难。因此,将品质函数中的均值和协方差定义为权重系数的函数,由此简化模型结构并方便其求解;虽然品质函数中仅包含参数权重系数,但结构比较复杂,难以求得参数的解析式。最后,采用非线性共轭梯度法（CGM）求解参数,该方法仅需利用品质函数值和参数梯度值,降低了参数求解的复杂性,并且收敛快,可以得到全局最优解。结果 为了有效而准确地验证提出的分割方法,分别采用本文算法和对比算法对合成图像和高分辨率遥感图像进行分割实验,并定性和定量地评价和分析了实验结果。实验结果表明本文方法的有效抗噪性,并得到很好的分割结果。从参数估计结果可以看出,本文算法有效简化了模型参数,并获得全局最优解。结论 提出一种融入邻域作用的高斯混合分割模型及其简化求解方法,实验结果表明,本文算法提高了算法的抗噪性,有效地简化了模型参数,并得到全局最优参数解。本文算法对具有噪声的高分辨率遥感影像广泛适用。     

小波域隐Markov交叠树模型及块效应评价

本文针对小波域隐Markov树模型(hidden Markov tree model,HMT)的块效应问题,分析了块效应的产生机理,给出了以图像去噪为基础的块效应评价准则,并提出小波域隐Markov交叠树模型(hidden Markov overlappmg tree model,HMOLT)和基于该模型的图像去噪算法。该模型通过对每个节点的数据扩展,使每个节点包括相邻的3个(1维)或9个(2维)小波系数,实现同一尺度相邻节点数据的交叠,有效地减轻HMT因树状结构而产生的块效应。实验表明,本文给出的模型和去噪算法,无论是在均方误差(MSE)、块效应指标,还是在主观视觉方面,都优于HMT和基于HMT的去噪算法。     

基于PSO的Markov随机场在医学图像分割中的应用

研究了应用粒子群优化算法（PSO）优化Markov随机场方法对磁共振图像进行分割的算法。建立了基于马尔可夫随机场的图像分割模型,针对马尔可夫随机场图像模型的局部相关特性和最大后验概率估计,将粒子群优化算法应用于该模型,快速获得图像分割目标的全局最优解。实验数据表明该方法的高效性。     

基于路网层次收缩的快速分布式地图匹配算法

地图匹配是轨迹数据挖掘的基本操作,在许多空间数据智能场景中都非常有用.基于隐马尔可夫模型(hidden Markov model,HMM)的地图匹配算法具有较高的准确率,应用最为广泛,但其计算效率较低,难以应对实时性要求较高的大规模轨迹情形.提出了一个基于路网层次收缩的分布式地图匹配框架CHMM,能够对大规模的轨迹数据...     

基于双门限的第一、第二心音自动识别方法

为提高心音检测算法对异常心音的识别率,提出一种基于双门限的第一心音(S1)和第二心音(S2)自动识别方法,通过海明窗进行滤波预处理,采用改进型希尔伯特-黄变换提取心音包络,利用双门限法对心音进行分段,使用临床知识对S1和S2进行自动识别。实验结果表明,该方法能够准确识别正常心音和异常心音中的S1和S2。     

基于小波域层次Markov模型的图像分割

针对两个状态的有限高斯混合模型逼近小波系数的不足和小波域隐马尔可夫树标号场相互独立的缺点,提出了一种基于小波域层次马尔可夫模型的图像分割算法,这种模型用有限通用混合模型逼近小波系数的分布,使有限高斯混合模型只是其一种特殊情况;在标号场的先验模型确定上,利用马尔可夫模型描述标号场的局部作用关系,给出标号场的具体表达式,克服了小波域马尔可夫树模型标号场相互独立的不足,然后利用贝叶斯准则,给出相应的分割因果算法。该模型不仅具有空域马尔可夫模型有效的递归算法的优点,同时具有小波域隐马尔可夫树模型中的马尔可夫参数变尺度行为。最后用真实的图像和合成图像同几种分割方法进行了对比实验,实验结果表明了本文算法的有效性和优异性。     

基于隐高斯混合模型的人脑MRI分割方法

针对传统的高斯混合模型的抗噪性能和鲁棒性较差的缺点,提出一种基于隐高斯混合模型的人脑MRI分割方法。传统的高斯混合模型由于忽略了空间信息和未考虑分割结果的分布情况导致模型不完整。针对这些缺点,把分割结果的概率密度函数作为隐含数据引入到高斯混合模型,建立了非线性加权的隐高斯混合模型;同时引入了含空间信息与平滑系数的高斯权重置指数;运用期望最大化算法与牛顿迭代法对类均值,类方差以及平滑系数进行求解,最后根据最大后验概率准则得到人脑MRI的最终分割结果。经实验表明,提出的方法对人脑MRI具有很好的鲁棒性与抗噪性能。     

基于自适应阈值的心音分段方法仿真研究

针对心音信号频率低、易受干扰并含有大量杂音的特点,提出了一种心音分段新方法。首先,采用dB6小波进行5层小波分解做心音信号降噪处理;然后,采用了一种提取降噪后心音信号连续平均能量包络的方法;最后,根据连续平均能量包络及自相关函数提出了一种自适应阈值心音分段方法。仿真结果表明,该方法所提取的心音信号包络特征更稳健,提出的分段算法与基于短时能熵比法和短时自相关函数法等心音分段算法相比,本文所提算法分段准确度更高。     

Improved HMRF for Remote Sensing Image Segmentation

The traditional Markov random field algorithm used for image segmentation is often associated with some known problems,such as unsmooth edges of the segmented regions due toimage noise and abnormal pixels values,thus,subsequently inaccuracy segmentation results.On account of this phenomenon,an algorithm that follows the hidden Markov random field which is based on finite Gaussian mixture model is put forward.First,the initial segmentation results are obtained by replacing traditional K-means method with the Expectation Maximization (EM) algorithm,and they are smoothedby using the bilateral filter.Next,the finite Gaussian mixture model and the Potts modelare used to model the feature field and the mark field,and the EM algorithm is used for its parameter estimationto obtain the feature field energy and the mark field energy.Finally,the energy function is minimized by using the Iterative Condition Model (ICM) algorithm in order to achievean optimal segmentation result.Experimental results show that our approach achieved a more efficient result by comparingto the classical MRF method and the traditional HMRF method,and the probabilistic rand index and global consistency error indicators are better than that of existing     

Heart sound as a biometric

In this paper, we propose a novel biometric method based on heart sound signals. The biometric system comprises an electronic stethoscope, a computer equipped with a sound card and the software application. Our approach consists of a robust feature extraction scheme which is based on cepstral analysis with a specified configuration, combined with Gaussian mixture modeling. Experiments have been conducted to determine the relationship between various parameters in our proposed scheme. It has been demonstrated that heart sounds should be processed within segments of 0.5 s and using the full resolution in frequency domain. Also, higher order cepstral coefficients that carry information on the excitation proved to be useful. A preliminary test of 128 heart sounds from 128 participants was collected to evaluate the uniqueness of the heart sounds. The HTK toolkit produces a 99% recognition rate with only one mismatch. Next, a more comprehensive test consisting almost 1000 heart sounds collected from 10 individuals over a period of 2 months yields a promising matching accuracy of 96% using the proposed feature and classification algorithm. A real-time heart sound authentication system is then built and can be used in two modes: to identify a particular individual or to verify an individual's claimed identity.     

Hidden Markov model-based classification of heart valve disease with PCA for dimension reduction

In this study, a biomedical system to classify heart sound signals obtained with a stethoscope, has been proposed. For this purpose, data from healthy subjects and those with cardiac valve disease (pulmonary stenosis (PS) or mitral stenosis (MS)) have been used to develop a diagnostic model. Feature extraction from heart sound signals has been performed. These features represent heart sound signals in the frequency domain by Discrete Fourier Transform (DFT). The obtained features have been reduced by a dimension reduction technique called principal component analysis (PCA). A discrete hidden Markov model (DHMM) has been used for classification. This proposed PCA-DHMM-based approach has been applied on two data sets (a private and a public data set). Experimental classification results show that the dimension reduction process performed by PCA has improved the classification of heart sound signals.     

VBI-MRF model for image segmentation

In statistical image segmentation, the distribution of pixel values is usually assumed to be Gaussian and the optimal result is believed to be the one that has maximum a posteriori (MAP) probability. In spite of its prevalence and computational efficiency, the Gaussian assumption, however, is not always strictly followed, and hence may lead to less accurate results. Although the variational Bayes inference (VBI), in which statistical model parameters are also assumed to be random variables, has been widely used, it can hardly handle the spatial information embedded in pixels. In this paper, we incorporate spatial smoothness constraints on pixels labels interpreted by the Markov random field (MRF) model into the VBI process, and thus propose a novel statistical model called VBI-MRF for image segmentation. We evaluated our algorithm against the variational expectation-maximization (VEM) algorithm and the hidden Markov random field (HMRF) model and MAP-MRF model based algorithms on both noise-corrupted synthetic images and mosaics of natural texture. Our pilot results suggest that the proposed algorithm can segment images more accurately than other three methods and is capable of producing robust image segmentation.     

Spatially Constrained Student’s <Emphasis Type="Italic">t</Emphasis>-Distribution Based Mixture Model for Robust Image Segmentation

The finite Gaussian mixture model is one of the most popular frameworks to model classes for probabilistic model-based image segmentation. However, the tails of the Gaussian distribution are often shorter than that required to model an image class. Also, the estimates of the class parameters in this model are affected by the pixels that are atypical of the components of the fitted Gaussian mixture model. In this regard, the paper presents a novel way to model the image as a mixture of finite number of Student’s t-distributions for image segmentation problem. The Student’s t-distribution provides a longer tailed alternative to the Gaussian distribution and gives reduced weight to the outlier observations during the parameter estimation step in finite mixture model. Incorporating the merits of Student’s t-distribution into the hidden Markov random field framework, a novel image segmentation algorithm is proposed for robust and automatic image segmentation, and the performance is demonstrated on a set of HEp-2 cell and natural images. Integrating the bias field correction step within the proposed framework, a novel simultaneous segmentation and bias field correction algorithm has also been proposed for segmentation of magnetic resonance (MR) images. The efficacy of the proposed approach, along with a comparison with related algorithms, is demonstrated on a set of real and simulated brain MR images both qualitatively and quantitatively.