基于均值偏移的灰度图像分割方法

针对灰度图像分割往往存在的过分割或欠分割问题，提出了一种基于均值偏移的图像分割方法．该方法通过联合像素的空间位置和灰度特征，建立图像的特征矢量，构造基于像素的位置和灰度的改进核函数直方图．采用均值偏移算法搜索图像的特征模式，并以此对图像进行平滑滤波和分割．对以地物为背景的图像分割结果表明，该方法既能抑制具有纹理的大片背景，又能提取出面积较小且轮廓清晰的物体，分割的物体完整且符合人眼视觉，较有效地避免了图像过分割和欠分割的问题．     

舰船尾迹光学信号特征的直方图提取方法

现有舰船尾迹光学信号特征提取方法普遍存在运算复杂、处理速度不快等问题,研究基于直方图分析的舰船尾迹光学信号特征快速提取方法。根据舰船尾迹图像直方图具有明显的双峰特征,提出用峰值点分布密集程度kdd和尾迹区与海水背景区像素灰度值均值比Ci2个参数来表征舰船尾迹光学信号特征强度,通过专门研制的海上特征提取实验装置进行特征提取实验分析。分析结果表明:这2个参数能定量可靠地描述舰船尾迹光学信号特征强度的变化规律,并且在特征提取中具有简单快速的优势,从读进一张舰船尾迹图像到利用MATLAB软件计算出其特征参数值,电脑处理时间约为0.07 s。     

基于直方图均衡化的Robinson图像边缘检测算法

针对图像边缘检测,现有Robinson相关算法存在效率低、阈值设定随机性大、易出现伪边缘等问题,提出一种改进Robinson的图像边缘检测算法。该算法利用直方图均衡化对图像进行增强,然后将Robinson算子原有的八方向梯度依照两两垂直原则组合为八组,分别计算每组梯度的范数,并取其最大值作为该像素点的梯度。最后取整幅图像的灰度均值作为阈值来识别图像的边缘像素和背景像素。实验表明,相对于现有相关算法,该算法检测结果更加清晰完整,同时避免了传统算子人为设定阈值随机性大的问题。     

一种基于梯度方向直方图的直线轮廓提取新方法

直线轮廓检测是计算机视觉领域中的一个基本问题。在靶场光测图像分析中,通过提取导弹、火箭等目标的直线轮廓,可以得到目标的三维姿态参量。提出了一种基于梯度方向直方图的直线轮廓提取新方法。梯度方向直方图被定义为具有相同梯度方向的图像点的梯度幅值之和。利用梯度方向直方图可以很方便地确定图像上边缘方向,根据此方向可在图像上搜索直线边缘的位置。由于同时利用了梯度的幅值和方向信息,所以该方法能自动地提取直线边缘而无需阈值。通过在实际图像中提取直线边缘,证明了该方法的有效性。     

基于灰度冗余图像融合增强研究

为了改善原图像直方图像素灰度分布集中于低灰度级,与经过常规直方图均衡化处理的图像直方图像素灰度分布集中于高灰度级且均具有灰度冗余的图像增强效果,提出了一种新的图像增强算法.对原始图像进行常规直方图均衡处理,并对原始图像与进行了常规直方图均衡处理的图像分别在尽可能大的范围内进行映射,使两者变换后都尽可能去除灰度冗余而有较大的动态范围.取变换后的两图像各自的优点,融合成一幅效果最好的图像.实验结果验证了理论分析的正确性.     

基于背景加权空间直方图的目标跟踪

针对传统目标跟踪算法中存在的特征鲁棒性不强的问题,提出了一种基于背景加权空间直方图的目标跟踪算法。算法通过综合背景加权直方图和空间直方图二者各自的优势,增强了特征描述的鲁棒性,进而在Mean Shift跟踪框架下实现了对运动目标的跟踪。仿真实验与定量分析表明,所提算法能够实现对目标的稳定跟踪,跟踪所得的平均中心位置误差较传统算法降低了80%以上。     

基于梯度的区域生长和距离直方图的快速圆检测方法EI北大核心CSCD

针对基于Hough变换类圆检测算法所需设置参数较多和基于距离直方图的算法计算量大等问题,提出了一种基于梯度的区域生长和距离直方图的快速圆检测方法(GHC)。该算法通过利用梯度模值和方向进行区域生长的方法得到若干圆弧线段支撑区域;选取弧线段上的三个坐标点求解该圆弧段对应的圆心和半径并求解出正方形适应区域;将每条圆弧线段上的所有点向其适应区域内各坐标点进行投影并统计距离的累加值;综合全图距离直方图,精确地求解出图像中包含各圆的圆心和半径并进行完整度校验。通过实验表明,相比基于距离直方图的圆检测算法(HBCD)和随机Hough变换算法(RHT),该法对不同尺寸、完整度的单圆或多圆均有良好的检测效果,具有较强的稳健性和较小的空间、时间复杂度。     

基于车载LiDAR点云的道路提取方法

针对提取道路点云聚类方法存在欠分割、过分割的问题,提出了一种基于坡度滤波算法和改进欧式距离的区域生长算法相结合的道路点云提取方法。原始点云数据量大且繁杂,采用统计分析进行预处理,去除一定数量悬空的噪声,减少数据量;为防止点云数据精度损失,对预处理后的点云按照格网进行划分,结合坡度滤波算法,去除非地面点干扰,获取地面点云;以法向量夹角和欧氏距离为约束条件,采用改进的区域生长算法提取路面点云。使用两组不同场景下的车载点云数据进行试验,证明了该方法的有效性。     

基于灰度聚类算法的红外图像增强研究

根据红外灰度图像的特点，提出了一种基于K-均值聚类的图像增强的新算法。该算法首先根据具体图像确定K值，其次对红外图像的辐射温度数据进行统计学习，把不同温度值按升序排列，然后按等差原则选取温度值作为初始聚类中心，再依据初始聚类中心采用K-均值聚类算法对温度进行聚类，最后由聚类结果对图像进行自适应增强。通过对红外灰度图像进行实验，得到了满意的结果: 对比直方图均衡，具有更丰富的图像细节信息和层次感，视觉效果更好。     

一种基于灰度聚合直方图评价边界融合效果的新方法

针对目标边界与背景融合效果客观评价的问题,基于聚合度的概念,结合伪装效果评价要求,利用边界图像的灰度信息及其空间分布信息,通过统计伪装样本数据,确定聚合度的滤波阈值,提出了一种基于归一化灰度聚合直方图评价边界融合效果的新方法.实验结果表明,该方法不仅能够有效地表征目标边界与背景的融合效果,其评价结果与人眼判读结果吻合,...     

A histogram-based segmentation method for characterization of self-assembled hexagonal lattices

Lattice characterization techniques are often used to quantify the effects of different anodization conditions on nano-porous anodized aluminum oxides. In this work, we develop a comprehensive hexagonal lattice characterization method to evaluate the amount of ordering of the lattice and localize the domains of the image and report their characteristics. A robust preprocessing is proposed to find pores’ centroids. Different domains of SEM images usually have different orientations. Pores orientation distribution is analyzed using angle-histogram. The valleys of angle-histogram are employed as thresholds to separate different dominant orientations. We show that using orientation as a distinguishing feature of different domains, significantly improves the robustness of the algorithm against tolerance parameters. Some new parameters are introduced to exactly characterize each of the domains and the whole lattice.     

An automatic cerebellum extraction method in T1-weighted brain MR images using an active contour model with a shape prior

Purpose

The objective of this paper was to automatically segment the cerebellum from T1-weighted human brain magnetic resonance (MR) images.

Materials and Methods

The proposed method constructs a cerebellum template using five sets of 3-T MR imaging (MRI) data, which are used to determine the initial position and the shape prior of the cerebellum for the active contour model. Our formulation includes the active contour model with shape prior, which thereby maintains the shape of the template. The proposed active contour model is sequentially applied to sagittal-, coronal- and transverse-view images. To evaluate the proposed method, it is applied to BrainWeb data and a 3-T MRI data set and compared with FreeSurfer with respect to performance assessment metrics.

Results

The segmented cerebellum was compared with the results from FreeSurfer. Using the manually segmented cerebellum as reference, we measured the average Jaccard coefficients of the proposed method, which were 0.882 and 0.885 for the BrainWeb data and 3-T MRI data set, respectively.

Conclusion

We presented the active contour model with shape prior for extracting the cerebellum from T1-weighted brain MR images. The proposed method yielded a robust and accurate segmentation result.     

基于投影的灰度图像特征提取

采用自顶向下基于知识特征的提取方法 ,在飞机目标红外特性分析的基础上 ,用三维灰度图像投影分解成两个二维平面图像 ,分别提取它们的边缘特征、不变性角特征和区域特征 ,并对特征进行了融合 ,得到飞机目标的灰度图像特征。结果证明 ,该方法大大简化了特征提取系统的复杂性 ,便于硬件的实现     

Optimization of tissue segmentation of brain MR images based on multispectral 3D feature maps

The purpose of this work was to optimize and increase the accuracy of tissue segmentation of the brain magnetic resonance (MR) images based on multispectral 3D feature maps. We used three sets of MR images as input to the in-house developed semi-automated 3D tissue segmentation algorithm: proton density (PD) and T2-weighted fast spin echo and, T1-weighted spin echo. First, to eliminate the random noise, non-linear anisotropic diffusion type filtering was applied to all the images. Second, to reduce the nonuniformity of the images, we devised and applied a correction algorithm based on uniform phantoms. Following these steps, the qualified observer "seeded" (identified training points) the tissue of interest. To reduce the operator dependent errors, cluster optimization was also used; this clustering algorithm identifies the densest clusters pertaining to the tissues. Finally, the images were segmented using k-NN (k-Nearest Neighborhood) algorithm and a stack of color-coded segmented images were created along with the connectivity algorithm to generate the entire surface of the brain. The application of pre-processing optimization steps substantially improved the 3D tissue segmentation methodology.     

A technique for single-channel MR brain tissue segmentation: Application to a pediatric sample

A segmentation method is presented for gray matter, white matter, and cerebrospinal fluid (CSF) in thinsliced single-channel brain magnetic resonance (MR) scans. The method is based on probabilistic modeling of intensity distributions and on a region growing technique. Interrater and intrarater reliabilities for the method were high, and comparison with phantom studies and hand-traced results from an experienced rater indicated good validity. The method was designed to account for spatially dependent image intensity inhomogeneities. Segmentation of MR brain scans of 105 (56 male and 49 female) healthy children and adolescents showed that although the total brain volume was stable over age 4–18, white matter increased and gray matter decreased significantly. There were no sex differences in total gray and white matter growth after correction for total brain volume. White matter volume increased the most in superior and posterior regions and laterality effects were seen in hemisphere tissue volumes. These findings are consistent with other reports, and further validate the segmentation technique.     

Mapping the parameter space of a T2-dependent model of water diffusion MR in brain tissue

We present a new model for describing the diffusion-weighted (DW) proton nuclear magnetic resonance signal obtained from normal grey matter. Our model is analytical and, in some respects, is an extension of earlier model schemes. We model tissue as composed of three separate compartments with individual properties of diffusion and transverse relaxation. Our study assumes slow exchange between compartments. We attempt to take cell morphology into account, along with its effect on water diffusion in tissues. Using this model, we simulate diffusion-sensitive MR signals and compare model output to experimental data from human grey matter. In doing this comparison, we perform a global search for good fits in the parameter space of the model. The characteristic nonmonoexponential behavior of the signal as a function of experimental b value is reproduced quite well, along with established values for tissue-specific parameters such as volume fraction, tortuosity and apparent diffusion coefficient. We believe that the presented approach to modeling diffusion in grey matter adds new aspects to the treatment of a longstanding problem.     

A modified fuzzy clustering algorithm for operator independent brain tissue classification of dual echo MR images.

Methods for brain tissue classification or segmentation of structural magnetic resonance imaging (MRI) data should ideally be independent of human operators for reasons of reliability and tractability. An algorithm is described for fully automated segmentation of dual echo, fast spin-echo MRI data. The method is used to assign fuzzy-membership values for each of four tissue classes (gray matter, white matter, cerebrospinal fluid and dura) to each voxel based on partition of a two dimensional feature space. Fuzzy clustering is modified for this application in two ways. First, a two component normal mixture model is initially fitted to the thresholded feature space to identify exemplary gray and white matter voxels. These exemplary data protect subsequently estimated cluster means against the tendency of unmodified fuzzy clustering to equalize the number of voxels in each class. Second, fuzzy clustering is implemented in a moving window scheme that accommodates reduced image contrast at the axial extremes of the transmitting/receiving coil. MRI data acquired from 5 normal volunteers were used to identify stable values for three arbitrary parameters of the algorithm: feature space threshold, relative weight of exemplary gray and white matter voxels, and moving window size. The modified algorithm incorporating these parameter values was then used to classify data from simulated images of the brain, validating the use of fuzzy-membership values as estimates of partial volume. Gray:white matter ratios were estimated from 20 twenty normal volunteers (mean age 32.8 years). Processing time for each three-dimensional image was approximately 30 min on a 170 MHz workstation. Mean cerebral gray and white matter volumes estimated from these automatically segmented images were very similar to comparable results previously obtained by operator dependent methods, but without their inherent unreliability.     

Modeling brain tissue volumes over the lifespan: quantitative analysis of postmortem weights and in vivo MR images

Normative measurements of brain gray matter and white matter tissue volumes across the lifespan have not yet been established. The purpose of this article was to use mathematical modeling and analytical functions to demonstrate the growth trajectory of gray matter and white matter from age 0 to age 90. For each gender, brain weight functions were generated by utilizing existing autopsy data from 4400 subjects. Brain gray matter, white matter and lateral ventricular volumes were measured from 39 MR volumes of normal individuals. These were converted to weight by multiplying the tissue volumes by the specific gravity of that tissue. White matter volumes were described by a saturating exponential function, and the gray matter volume function was calculated by subtracting the white matter weight function from the brain weight function. For each gender, equations were generated for white matter and gray matter volumes as a function of age over the lifespan.     

PDE-based spatial smoothing: a practical demonstration of impacts on MRI brain extraction, tissue segmentation and registration

Spatial smoothing is typically used to denoise magnetic resonance imaging (MRI) data. Gaussian smoothing kernels, associated with heat equations or isotropic diffusion (ISD), are widely adopted for this purpose because of their easy implementation and efficient computation, but despite these advantages, Gaussian smoothing kernels blur the edges, curvature and texture of images. To overcome these issues, researchers have proposed anisotropic diffusion (ASD) and non-local means [i.e., diffusion (NLD)] kernels. However, these new filtering paradigms are rarely applied to MRI analyses. In the current study, using real degraded MRI data, we demonstrated the effect of denoising using ISD, ASD and NLD kernels. Furthermore, we evaluated their impact on three common preprocessing steps of MRI data analysis: brain extraction, segmentation and registration. Results suggest that NLD-based spatial smoothing is most effective at improving the quality of MRI data preprocessing and thus should become the new standard method of smoothing in MRI data processing.     

基于格雷码的分区间相位展开方法

格雷码因具有良好的鲁棒性和抗噪性,被广泛应用到结构光投影三维成像方法中。在三维测量过程中,由于设备以及其他环境噪声的影响,格雷码方法解码条纹级次边沿和截断相位边沿通常无法处于理想的对齐状况,使得展开的相位出现跳变现象。为了更好地避免级次跳变误差,使得边沿跳变区域的容错宽度更大,提出基于格雷码的分区间相位展开方法。在互补格雷码基础上增加一幅格雷码图像,利用所有格雷码解得附加码字,通过对附加码字进行不同位移量的条纹级次映射,得到2个辅助条纹级次。利用所有条纹级次,对截断相位进行分区间相位展开,在边沿跳变区域错误大于半个周期时,仍能获取到无跳变现象的展开相位。实验结果表明,当边沿错误区域宽度小于3/4个条纹周期宽度时,可以有效避免级次跳变产生的误差。