一种用于前列腺区域分割的改进水平集算法

前列腺区域的精确分割是提高计算机辅助前列腺癌诊断准确率的重要前提.本文提出了一种新的精确的前列腺区域分割模型,分为4个步骤：首先,读取T₂加权磁共振（MR）图像;其次,利用半径为5个像素的8邻域模板（8x5）的局部二值模式（LBP）特征模板计算前列腺磁共振图像的LBP特征图;然后,利用改进的距离正则化水平集（DRLSE）模型对特征图进行分割,提取前列腺粗轮廓;最后将原始水平集能量函数进行优化,构造一个新的能量函数,提取局部灰度信息和梯度信息,并在此新的能量函数的基础上,将粗轮廓迭代演化为最终的细轮廓.本文将该模型在203组来自于国际光学与光子学学会-美国医学物理学家协会-国家癌症研究所（SPIE-AAPM-NCI）前列腺MR分类挑战数据库的T2W磁共振图像上进行了测试,并与医生手工分割结果进行了比较,结果表明本文提出模型得到的分割结果的Dice系数为0.94±0.01,相对体积差（RVD）为-1.21%±2.44%,95% Hausdorff距离（HD）为6.15±0.66 mm;与文献中现有的分割模型相比,使用本文提出的模型得到的前列腺区域分割结果更接近于手工分割的结果.     

Chan-Vese模型两相自适应窄带的阴影区检测方法

为得到快速高精度的声呐图像阴影区检测效果,提出Chan-Vese模型两相自适应窄带检测方法。利用各向异性二阶邻域马尔可夫模型估计声呐图像的纹理特征参数,实现原始图像平滑去噪;由块方式的k-均值聚类算法确定图像的初始两类分割,初步确定阴影区大致位置,并根据此大致位置,自适应初始化零水平集函数,来减少人为干预,提高检测速度;在此基础上,提出建立Chan-Vese模型两相窄带水平集进行声呐图像检测,完成局部寻优,排除全局图像中孤立区对检测的影响,使阴影区检测结果更加精确。通过对真实声呐图像的检测实验结果分析,验证提出的检测方法能够去除原始图像的部分噪声,提高检测精度和速度,有一定的自动性和适应性。      

结合稀疏编码和空间约束的红外图像聚类分割研究

提出了结合稀疏编码和空间约束的红外图像聚类分割新算法, 在稀疏编码的基础上融合聚类算法, 扩展了传统的基于K-means聚类的图像分割方法. 结合稀疏编码的聚类分割算法能有效融合图像的局部信息, 便于利用像素之间的内在相关性, 但是对于分割会出现过分割和像素难以归类的问题.为此, 在字典的学习过程中, 将原子的聚类算法引入其中, 有助于缩减字典中原子所属类别的数目, 防止出现过分割; 考虑到像素及其邻域像素具有类别属性一致性的特点, 引入了空间类别属性约束信息, 并给出了一种交替优化算法. 联合学习字典、稀疏系数、聚类中心和隶属度, 将稀疏编码系数同原子对聚类中心的隶属程度相结合, 构造像素归属度来判断像素所属的类别. 实验结果表明, 该方法能够有效提高红外图像重要区域的分割效果, 具有较好的鲁棒性. 关键词： 图像分割 稀疏编码 聚类 空间约束     

Shadow regions detection algorithm by adaptive narrowband two-phase Chan-Vese model

An adaptive narrowband two-phase Chan-Vese(ANBCV) model is proposed for im?proving the shadow regions detection performance of sonar images. In the first noise smoothing step, the anisotropic second-order neighborhood MRF(Markov Random Field, MRF) is used to describe the image texture feature parameters. Then, initial two-class segmentation is processed with the block mode /c-means clustering algorithm, to estimate the approximate position of the shadow regions. On this basis, the zero level set function is adaptively initialized by the approximate position of shadow regions. ANBCV model is provided to complete local op?timization for eliminating the image global interference and obtaining more accurate results.Experimental results show that the new algorithm can efficiently remove partial noise, increase detection speed and accuracy, and with less human intervention.     

基于伪魏格纳分布分解的合成孔径雷达图像目标与阴影分割

在二维魏格纳分布的框架内,针对魏格纳变换的交叉项问题和计算量大的问题,提出了合成孔径雷达图像局部伪魏格纳变换的目标和目标阴影的分割方法.首先,将合成孔径雷达图像进行二维伪魏格纳变换,得到各像素点的二维能量谱图|然后提取各像素点的二维能量谱图对应位置值形成多个不同频段的与原图像同大小的能量谱图|最后,对不同频段的能量谱图采用不同的处理方法后,将各能量谱图相加处理后形成区域标识图像,最终得到原图像的目标和目标阴影分割图像.本文利用该方法对MSTAR切片图像进行了分割试验,并对分割图像与频谱最大值距离或方位分割算法和基于双参量CFAR与隐马尔科夫联合分割算法进行了分割图像对比度对比.实验结果表明,采用本文算法的合成孔径雷达分割图像,对比度明显提高,且保留了目标图像细节.     

Study of mutual information multimodality medical image registration based on modified simplex optimization method

Because of a different imaging mechanism and highly complexity of body tissues and structures. Different modality medical images provide non-overlay complementary information. This has very important significance for multimodal medical image registration. Image registration is the first and key part of problem to be solved in the integrations. When the spatial position of two medical images is same, the registration could be achieved. For two CT and PET images, the principal axis method is adopted to achieve the rough registration. The modified simplex algorithm is employed to implement global search using the mutual information as similarity measure. The initial registration parameters are achieved through principal axis Based on the results of test, improved simplex method can adjust reflecting distance. Stepped-up optimization algorithm on the new experimental points through the methods of “reflection”, “enlargement”, “shrinkage” or “global systolic”. A mutual information registration based on modified simplex optimization method is presented in this paper to improve the speed of medical image registration.Results indicate that the proposed registration method prevents the optimizing process from falling into local extremum and improves the convergence speed while keeping the precision. The accurate registration of multimodal image with different resolutions is achieved.     

Target extraction in forward-looking infrared images using fuzzy thresholding via local region analysis

In this paper, a target extraction method in forward-looking infrared (FLIR) images based on fuzzy thresholding which used local characteristics, bi-modality and adjacency, is proposed. The bi-modality represents how a pixel is classified into a part of a target using distribution of pixel values in a local region, and the adjacency is a measure to represent how far each pixel is from the target region. Segmentation is processed by the following: First, membership values for each pixel are calculated using bi-modality and adjacency. Second, fuzzy thresholding is performed to extract the target from the background. Finally, we extract the precise target in the thresholded image by post-processing. To evaluate the performance of the proposed target extraction method, we compare the proposed method with other segmentation methods using various FLIR images. Experimental results show that the proposed algorithm has good segmentation performance.     

Local adaptive sampling for wireless sensor network powered by energy harvesting

For a sensor network, energy limitation is always a key factor to affect the continuous work of a sensor node. A good idea is harvesting energy from the environment to support the node to work continuously. However, energy from environment is varied with time, weather and season. So in order to use the varied environment energy, it is necessary to find a way to achieve real-time monitoring and adaptive working. In this paper, an algorithm called “Adaptive Sampling” was proposed to adapt the sample mode to the present energy condition. Simulation proves that the algorithm can make the CO₂ sensor flexibly achieve adaptive sampling under different energy condition with the least MSE 2.7767. This algorithm can be widely used in wireless sensor network power by energy harvesting for local adaptive sampling.     

一种基于区域分割与跟踪的多视点视频校正算法

针对多视点图像系统中视点图像颜色不一致的问题,提出了基于区域分割与跟踪的多视点视频校正算法.采用3维高斯混合模型来描述颜色信息,利用期望-最大算法来精炼模型参量,并通过自适应聚类和概率平滑操作来得到精确的分割图像.这样建立起多视点图像分割区域间的局部映射关系,并利用这种局部映射关系对全局图像进行校正.最后利用视频跟踪技术实现对视频图像的校正.实验结果表明,该算法能消除颜色过饱和或颜色区域混淆的影响,且具有较好的校正效果.     

Failures in the discrete models for flow duct with perforations: an experimental investigation

Acoustical experiments have been performed at low frequencies on perforated tubes with a back cavity by means of the “2 sources method” and are compared to classical models. The four elements of the transfer matrix of the device are measured with flow. The classical lumped model relates the sound pressure and the axial velocity on both sides of the lined region. Since this model fails, a new empirical model has been proposed to take into account the experimental data. The new transfer matrix of the measured device is calculated and the results fit surprisingly well with the experiments. It is therefore possible to make a segmentation model of the aeroacoustical behaviour of a perforated tube with a partitioned chamber.     

Depth information extraction with an aperture-rotating camera

This paper focuses on extracting depth information with an aperture-rotating camera. Compared with previous work, the proposed method is applicable for arbitrary rotation angle by making use of pixel registration to get pixel shift angle, and calculating the pixel shift along this angle. Besides, consumption time for shift angle is reduced by means of sampling. Compared with point-by-point method, the proposed method reduces the computation time from about 1 h to 1 min for a 15-megapixel image. Experimental results of a scene named “bottles” show that the depth value has a margin of error of 5%. Proposed method makes it possible to extract depth information with a single camera and expands the application of DSLR camera.     

Image segmentation based on hierarchical belief propagation with variable weighting parameters

The belief propagation (BP) algorithm is an efficient way to minimize the MRF energy for image segmentation. This paper proposes a hierarchical BP algorithm with variable weighting parameters (HBP-VW) to improve the segmentation accuracy of the BP-based algorithms. In the HBP-VW, two variable weighting parameters are introduced, the global parameter and the local parameter. The global parameter is used to overall adjust the influence of each part in the message update rule. The local parameter is designed to describe the local texture pattern for each site. Texture, remote sensing, and nature images are employed to test the proposed algorithm. Experimental results illustrate a better segmentation accuracy compared with other BP-based algorithms.     

基于马尔可夫随机场的改进Metropolis混凝土CT的图像分割方法

提出一种基于马尔可夫随机场改进的Metropolis模拟退火算法.该算法中阈值α的选取优化了Metropolis算法.根据Beyes理论将图像分割问题转化为最大后验概率求取问题,并给出了参量预测算法.在实验中,将本文提出的算法与ICM、传统的Metropolis和Gibbs采样模拟退火算法进行比较.结果表明改进的Metropolis算法在图像分割效率和分割准确度上都有明显的提高.通过混凝土CT图像分割实验,改进Metropolis的应用能够较完整地反映出混凝土材料的内部结构和缺陷.     

中医按摩机器人专家控制系统的研究

为改进传统模糊C均值聚类(FCM)算法对初始聚类中心敏感、易陷入局部收敛、抗噪性差、计算量大的问题,提出一种新的基于改进粒子群算法的快速模糊聚类图像分割方法(PSOFFCM)。方法首先利用自适应中值滤波对图像进行滤波处理,增强算法的鲁棒性;然后,将图像像素灰度值映射到二维直方图特征空间,作为聚类样本,优化FCM的目标函数,减少图像分割的计算量;最后,利用PSO算法代替FCM的梯度迭代过程,减弱了算法对初始聚类中心的依赖,同时增强全局搜索能力。实验结果表明,该方法不仅克服了FCM算法对初始聚类中心的依赖,而且抗噪能力强,收敛速度快,分割精度明显优于传统FCM。     

基于自适应扩散模型的单帧红外条纹非均匀性校正算法

针对红外焦平面成像系统存在列向条纹非均匀性的现象,采用了一种基于自适应PM扩散模型的非均匀校正新算法。首先,综合利用图像梯度信息和局部灰度统计信息,自适应计算PM模型的扩散阈值;然后将每列像素的PM模型估计值作为该列像素的期望值;最后采用最陡下降法迭代计算得到每列像元的校正参数,并对结果进行循环校正以提高校正效果。实验结果表明:该算法可以保护图像边缘信息,与同类算法相比,能够更有效地抑制条纹非均匀性,并且能够防止图像产生鬼影。     

Multiple small objects tracking based on dynamic Bayesian networks with spatial prior

This paper proposes an end-to-end algorithm for multiple small objects tracking in noisy video using a combination of Gaussian mixture based background segmentation along with a Dynamic Bayesian Networks (DBNs) based tracking. Background segmentation is based on an adaptive backgrounding method that models each pixel as a mixture of Gaussians with spatial prior and uses an online approximation to update the model, the spatial prior is constructed for small objects. Furthermore, we create observation model with hidden variable based on multi-cue statistical object model and employ Kalman filter as inference algorithm. Finally, we use linear assignment problem (LAP) algorithm to perform the models matching. The experimental results show the proposed method outperforms competing method, and demonstrate the effectiveness of the proposed method.     

基于局部和全局信息的自适应水平集图像分割

针对仅采用局部或全局信息无法快速准确分割灰度不均匀图像的问题,提出了一种基于局部和全局信息的自适应水平集图像分割模型。首先,利用图像局部信息和全局信息建立局部能量项和全局能量项,并且利用演化曲线轮廓内外小邻域的灰度均值差作为自变量,建立了权重函数模型,实现了局部能量项和全局能量项之间权重的自适应调整,提高了模型分割灰度不均匀图像的效率和准确性。其次,提出了一种新的能量惩罚项,避免了水平集函数的重新初始化,增强了数值计算的稳定性。最后,为验证模型的优越性,将模型与CV模型、LBF模型和LGIF模型进行了对比,并通过分割时间、迭代次数以及相似度等指标对分割结果进行了客观、定量分析。最终结果表明:该模型不但对初始轮廓具有较高鲁棒性,而且对灰度不均匀图像具有较高的分割准确性与分割效率。     

基于GFO和标记点分水岭算法的医学图像分割

传统的分水岭分割一般是在原始图像中根据边缘检测算子所得的边缘图进行计算,常规的边缘检测算子并没有引入图像的先验信息或形状约束。由于病理改变以及医学影像数据内在的模糊性,常规边缘检测算子很难引导分水岭算法收敛到正确的目标轮廓,由此导致传统分水岭算法容易受到图像噪声的干扰而"过分割"。在此情况下,提出利用基于广义模糊算子(GFO)的边缘检测算法来改进标记点分水岭分割。从实验结果看,提出的方法非常适合应用于临床医学图像分割。     

基于随机聚类的复杂背景建模与前景检测算法

为了构建鲁棒的背景模型和提高前景目标检测的准确性, 综合考虑同一位置的像素点在时间上的关联性和与其相邻像素的空间关联性, 基于经典的ViBe算法中的随机聚类思想提出了一种复杂背景建模和前景检测方法. 利用样本一致性原理, 采用前n帧序列图像得到初始化背景, 避免了Ghost现象的发生; 根据实际复杂背景的动态反馈获取自适应聚类阈值和自适应更新阈值进行随机聚类, 从而实现了对动态背景的适应性; 通过全局扰动阈值和局部像素级判断阈值的结合, 实现了对光照缓慢变化、快速变化以及突然变化的免疫性, 准确地分割前景目标. 对多组数据集的测试结果表明, 本文算法较大地提高了背景模型对动态背景、光照变化及相机抖动的复杂背景的适应性和鲁棒性. 算法还能很好地适用于红外图像检测运动目标的场合, 扩展了本算法的应用范围. 在没有进行任何图像预处理和形态学后处理情况下, 得到的原始前景检测精度优于其他对比算法.     

An adaptive multi-feature segmentation model for infrared image

Active contour models (ACM) have been extensively applied to image segmentation, conventional region-based active contour models only utilize global or local single feature information to minimize the energy functional to drive the contour evolution. Considering the limitations of original ACMs, an adaptive multi-feature segmentation model is proposed to handle infrared images with blurred boundaries and low contrast. In the proposed model, several essential local statistic features are introduced to construct a multi-feature signed pressure function (MFSPF). In addition, we draw upon the adaptive weight coefficient to modify the level set formulation, which is formed by integrating MFSPF with local statistic features and signed pressure function with global information. Experimental results demonstrate that the proposed method can make up for the inadequacy of the original method and get desirable results in segmenting infrared images.