基于表面法矢的散乱数据分割与几何特征提取

使用区域增长法进行散乱数据的区域分割以及二次曲面几何特征的提取.算法首先自动地布置种子区域,然后通过迭代/拟合这一循环过程来实现区域的增长.为了提高算法的可靠性,提出基于散乱数据表面法矢的二次曲面直接拟合方法.该方法根据特定类型二次曲面的几何性质,应用线性最小二乘技术求解其几何参数,从根本上解决以往二次曲面拟合算法因几何参数初值的设置精度不高而导致的求解效率低,进而失败的问题.试验结果表明提出的算法实现简单,且稳定可靠.     

Geometrical inspection of designed and acquired surfaces

In this study a series of procedures were implemented to compare acquired surfaces with the nominal data or to directly compare different scanned surfaces. In particular a morphological evaluation algorithm based on the extended Gaussian curvature (EGC) and a method to compare features based on aggregate normal orientation are presented. To perform the comparing feature method a simple procedure for segmentation was developed. The main characteristic of the two methods is robust behavior referring to the scan orientation. The procedures were implemented as software modules in a graphic environment.     

融合颜色与形状信息的铁谱磨粒链分割方法研究

为了对铁谱图像中的磨粒链进行有效分割,提高磨粒特征提取的精度,通过分析铁谱磨粒链图像不同区域的特点,提出一种融合铁谱图像颜色、形状特征信息的磨粒链分割方法。该方法首先基于形态学运算对磨粒链分割方法,对异常大磨粒进行提取并断开磨粒链黏连部分,然后利用标记分水岭与灰色聚类的方法对磨粒链进行分割,最后考虑到不同磨粒链颜色信息存在差异,结合自适应阈值法对灰色聚类进行改进,从而实现磨粒链的自适应分割。结果表明,相较于传统分割方法,提出的方法能有效避免过分割与欠分割,分割效果较好,适用性高,操作简单。     

基于TV-L~1分解的红外云图超分辨率算法

提出一种基于TV-L1分解的红外云图超分辨率算法。该方法采用原始-对偶算法求解TV-L1图像分解模型,将低分辨率云图分解为结构部分和纹理部分:对结构部分采用软决策自适应插值(SAI)处理;对纹理部分则基于非下采样Contourlet变换(NSCT)具有多方向和平移不变的特性,构造非线性增益函数对其NSCT变换域系数进行处理,然后对处理后的变换系数进行NSCT逆变换实现纹理增强。最后,将处理后的结构部分和纹理部分组合起来得到重构的高分辨率云图。实验结果表明,所提出的算法在视觉效果以及图像质量定量评价上均优于传统插值方法,在实现两倍超分辨率时,其峰值信噪比(PSNR)和结构相似度(SSIM)平均值分别提高了1.316 2~4.591 9dB和0.007 1~0.020 6;实现三倍超分辨率时PSNR和SSIM平均值分别提高了0.338 7~4.58dB和0.001 8~0.041 7。由于SAI插值和非下釆样Contourlet变换准确表示了云图的不同形态特征,故所提算法的超分辨率结果不但准确重建了云图中的结构部分,而且有效保持了红外云图纹理和边缘。     

基于分层多尺度形态学梯度修正的分水岭分割

形态学分水岭分割对图像中的噪声和非规则细节较为敏感, 常常导致较严重的过分割. 如果在分水岭分割之前采用线性滤波器进行平滑,可以在某种程度上消除噪声和非规则细节干扰造成的分水岭过分割, 但是可能使分割出的目标轮廓产生位置偏移. 为了能够在消除过分割的同时保持目标轮廓的位置不变, 提出了一种基于分层多尺度形态学梯度修正的分水岭分割方法. 首先对原始图像进行多尺度形态学滤波平滑; 然后根据形态学梯度图像的三维地貌体积对其进行分层多尺度修正, 自适应地确定修正所需的结构元素尺寸, 对于低梯度层级采用较大尺寸结构元素进行形态学闭运算, 消除因非规则细节产生过分割的非规则局部极小值, 而对较高梯度层则采用较小尺寸的结构元素, 保持区域轮廓的位置不变; 最后在修正梯度图像基础上, 运用标准分水岭变换实现图像分割. 实验结果表明, 该方法能够在消除过分割的同时, 较准确的保持目标轮廓的位置.     

基于补偿机制的NSCT域红外与可见光图像融合

针对传统基于非下采样Contourlet变换和脉冲耦合神经网络的图像融合方法易出现图像失真的缺点,本文提出一种基于小波变换与PCNN补偿的NSCT域内红外与可见光图像融合方法。首先将红外和可见光图像分别进行NSCT分解,得到低频分量和高频分量;然后对低频分量进行二维小波分解,得到1个低频子带和3个方向子带,对其低频子带采用局部能量加权的方法进行融合,其余3个子带采用绝对值取大的方法进行融合;NSCT分解的高频子带融合规则分为对最高层的融合和其他层的融合,最高层采用绝对值取大的方法进行融合,而其余层采用的是基于改进型的PCNN的方法进行融合;最后将得到的低频子带和高频子带进行NSCT重构获得融合图像。合成及真实图像集实验结果表明,本文算法相对于传统的融合方法增加了图像的纹理和细节信息,有效地抑制了图像失真问题,具有较高的融合精度与较快的融合效率。     

基于区域划分的多特征纹理图像分割

由于纹理图像的复杂性和多样性,仅依靠传统的单一特征实现纹理图像分割无法满足其对分割精度的要求。本文提出结合区域划分的多特征纹理图像分割方法。首先,依据像素灰度的空间相关性定义多个纹理特征;然后利用区域划分将图像域划分成不同子区域,待分割同质区域由这些子区域拟合而成;通过分别定义多个特征图像的同质区域之间的异质性势能函数和刻画各子区域邻域关系势能函数来定义全局势能函数,并构建非约束吉布斯概率分布,从而建立纹理分割模型;最后,采用M-H算法采样上述概率分布,从而获得最优图像分割结果。分别对模拟纹理图像、遥感图像、自然纹理图像和SAR海冰图像进行了分割实验,并与利用单一特征得到的分割结果进行对比分析,定性和定量的测试结果验证了算法的有效性。     

基于视觉显著性的太阳能电池片表面缺陷检测

现有基于机器视觉的太阳能电池片表面缺陷检测算法均是采用各种类型的数学模型来进行算法设计,为进一步提高检测准确率,从人眼仿生学角度出发,首次将人眼的视觉注意机制引入到太阳能电池片表面缺陷检测中,提出了一种基于视觉显著性的太阳能电池片表面缺陷检测算法。首先,对输入的太阳能电池片表面图像进行预处理,去除对检测有影响的噪声和栅线;其次,提出一种基于自学习特征的视觉显著性检测算法来大致定位缺陷区域;随后,提出一种视觉显著性和超像素分割相结合的算法来进一步精确定位缺陷区域;最后,通过形态学后处理得到最终检测结果。在包含多种缺陷类型的测试图像库上的主观和客观实验评估表明,该算法具有较高的检测准确率。     

Application of the morphological alpha shape method to the extraction of topographical features from engineering surfaces

In contrast to the mean-line based filters, morphological filters are function oriented and more suitable for the functional prediction of component performance. This paper presents a novel morphological method based on the alpha shape for the extraction of topographical features from engineering surfaces. Compared to the traditional implementation of morphological filters, the alpha shape method is more efficient in performance for large structuring elements. The resulting envelope follows the form of the surface all over such that the distortions caused the end effects are avoided. A series of measured surfaces from the automotive cylinder liner and the bioengineering artificial femoral heads are analyzed using the morphological alpha shape method. The topographical features are successfully extracted, enabling further physical and tribological analysis to the components.     

Correlating motif analysis and morphological filters for surface texture analysis

In contrast to the mean-line based evaluation system, motif analysis and morphological filters are two techniques oriented to the characterization of functional properties of surfaces. The motif combination procedure is consistent with the functionality of the morphological closing filter that insignificant peaks on the profile are suppressed. By linking the functionality of the structuring elements with motif combination criterions, morphological envelopes are computed efficiently. Reversely the morphological closing filter coupled with horizontal line-segment structuring elements with lengths equivalent to the motif limits for roughness and waviness provides an alternative for motif analysis. The proposed morphological method has a sound mathematical basis and is stable. An example of applying the empirical motif method (ISO 12085) and the morphological method is demonstrated. The motif parameters resulted from two methods reveal that they coincide with each other. Thus two distinct function oriented methods for surface texture evaluation are technically correlated by mutual exploitation.     

基于红外图像识别的电气设备温升检测

为了更好地利用红外热成像技术对电气设备故障进行识别和诊断的问题,提出了一种基于红外图像特征和种子区域生长法的设备温升检测方法。采用邻域平均法减少了红外图像的噪声干扰,提取出了红外图像RGB空间中的红色分量图及绿色分量图,应用种子区域生长法分别对两分量图进行了分割,先通过寻找局部最高温点划分区域,再计算各区域内形态学梯度筛选出有故障的高温点,并将该点所在区域作为种子区域从而实现种子区域的自动选取,将像素点4个方向上的最大梯度及像素点与种子点的灰度差作为种子生长的判定条件,用交集的方法将分割后的红色分量图和绿色分量图融合,提取出了设备温升过高区域。实验及研究结果表明,该方法能确定高温升区域,且轮廓清晰,为电气设备温升故障诊断提供依据。     

反求工程中过渡曲面特征提取算法研究

针对反求工程中常见的过渡曲面特征，提出了一种过渡曲面特征的提取算法。该算法包括数据分块和过渡曲面参数提取两部分，在数据分块算法中，通过数据精简，曲率估算和曲率比较等步骤，将过渡区域的数据点从原努点云数据中分离出来，在过渡曲面参数提取算法中，通过圆柱拟合和过渡区域跟踪算法，计算出一系列过渡曲面的截面线，该算法和已有的过渡曲面特征提取算法相比，无需人工交互，而且适用于等半径过渡曲面特征和变半径过渡曲面特征。     

Excel在光学实验数据处理中的应用

回归分析是一类数学模型,其研究对象是一个随机变量同一个或多个非随机变量的关系问题,在提出一元和多元线性回归的基础上,通过比较最小二乘法解法和Excel函数解法,指出Excel函数解法可以简化复杂的数学运算,并配以图表,给求解过程带来方便.     

结合多尺度圆形滤波与MS聚类 的疑似结节分割

肺部CT图像中疑似病灶感兴趣区域(ROI)的准确分割是肺部计算机辅助检测/诊断(CAD)的重要环节。本文提出结合Hessian矩阵滤波的均值漂移聚类肺部疑似病灶ROI区域分割算法。对原图像进行多尺度Hessian矩阵圆形滤波,图像中圆形的疑似结节病灶区域得到滤波增强、直线形的气管/血管区域得到抑制,将Hessian矩阵滤波后的形状特征、灰度、空间位置3种信息引入特征空间,将均值漂移聚类的核函数分解为3种特征信息所分别对应的核函数乘积形式,最后采用自适应计算带宽的方法确定每个待分割疑似区域的带宽进行均值漂移聚类分割。对来自LIDC等127个包含不同类型肺结节的病例进行实验,实验结果表明引入Hessian矩阵圆形滤波信息的均值漂移聚类能够分割出与血管或气管相连或者交叉的结节区域,去除ROI中包含的非结节区域,能有效分割出基于灰度信息难以分割的毛玻璃型(GGO)结节;对于3种类型的结节区域:血管相连结节(VPN)、毛玻璃型结节(GG0)、孤立性结节(SPN)分割平均准确率分别为92.80%、86.13%、95.08%。     

Microscopic retinal blood vessels detection and segmentation using support vector machine and K-nearest neighbors

The retina is the deepest layer of texture covering the rear of the eye, recorded by fundus images. Vessel detection and segmentation are useful in disease diagnosis. The retina's blood vessels could help diagnose maladies such as glaucoma, diabetic retinopathy, and blood pressure. A mix of supervised and unsupervised strategies exists for the detection and segmentation of blood vessels images. The tree structure of retinal blood vessels, their random area, and different thickness have caused vessel detection difficulties at machine learning calculations. Since the green band of retinal images conveys more information about the vessels, they are utilized for microscopic vessels detection. The current research proposes an administered calculation for segmentation of retinal vessels, where two upgrading stages depending on filtering and comparative histogram were applied after pre-processing and image quality improvement. At that point, statistical features of vessel tracking, maximum curvature and curvelet coefficient are extracted for each pixel. The extracted features are classified by support vector machine and the k-nearest neighbors. The morphological operators then enhance the classified image at the final stage to segment with higher accuracy. The dice coefficient is utilized for the evaluation of the proposed method. The proposed approach is concluded to be better than different strategies with a normal of 92%.     

Modified cuckoo search algorithm in microscopic image segmentation of hippocampus

Microscopic image analysis is one of the challenging tasks due to the presence of weak correlation and different segments of interest that may lead to ambiguity. It is also valuable in foremost meadows of technology and medicine. Identification and counting of cells play a vital role in features extraction to diagnose particular diseases precisely. Different segments should be identified accurately in order to identify and to count cells in a microscope image. Consequently, in the current work, a novel method for cell segmentation and identification has been proposed that incorporated marking cells. Thus, a novel method based on cuckoo search after pre‐processing step is employed. The method is developed and evaluated on light microscope images of rats’ hippocampus which used as a sample for the brain cells. The proposed method can be applied on the color images directly. The proposed approach incorporates the McCulloch's method for lévy flight production in cuckoo search (CS) algorithm. Several objective functions, namely Otsu's method, Kapur entropy and Tsallis entropy are used for segmentation. In the cuckoo search process, the Otsu's between class variance, Kapur's entropy and Tsallis entropy are employed as the objective functions to be optimized. Experimental results are validated by different metrics, namely the peak signal to noise ratio (PSNR), mean square error, feature similarity index and CPU running time for all the test cases. The experimental results established that the Kapur's entropy segmentation method based on the modified CS required the least computational time compared to Otsu's between‐class variance segmentation method and the Tsallis entropy segmentation method. Nevertheless, Tsallis entropy method with optimized multi‐threshold levels achieved superior performance compared to the other two segmentation methods in terms of the PSNR.     

A new partitioning process for geometrical product specifications and verification

In ISO Geometrical Product Specifications and Verification Standards (GPS), Feature operations are used to obtain ideal and non-ideal features. The formalization of such operations enables to reduce ambiguity and uncertainty within the activities of design, manufacture and metrology of mechanical products, and their scientific investigation contributes to develop a sound mathematical framework and formalisms for the comprehension of engineering practices and the development of new standards. Partitioning is a fundamental operation defined in ISO GPS standard which aims at decomposing a part into independent features or surface portions for further processing and analysis. In this paper, a state-of-the-art survey of partitioning and segmentation methods and techniques reported in the literature is conducted and a comprehensive classification is proposed. Thereafter, a new partitioning process is developed for partitioning into regions and recognizing each region as one of the seven invariance classes of surfaces. It proceeds in three main steps: initial partitioning based on shape index and curvedness, refined partitioning by slippage analysis and invariance class recognition by statistical evaluation. An intuitive shape color wheel is defined to visualize the partitioned features according to their corresponding invariance classes. Experiments and results on both nominal models and measured point clouds are presented to demonstrate the effectiveness of the proposed method.     

基于数学形态学的新方法在脑组织分割中的应用

针对人体脑部切片图像特点,提出了一种基于数学形态学的脑组织自动分割算法.该算法首先通过形态重构获得粗糙的脑组织区域,然后运用腐蚀和膨胀运算进行边界定位分割出了脑组织,最后对连续断层图像的分割结果进行了三维重建.结果表明该算法分割准确且自动化程度高,适合于大量序列切片图像的快速自动分割.     

基于彩色图像的运动目标分割方法

针对彩色图像Hue-saturation-intensity颜色模型各分量所携带的颜色信息不同的特点,结合区域分割算法在彩色图像中提取区域颜色特征,并将区域颜色特征作为局部阈值分割方法的阈值特征,提出一种基于图像区域颜色特征的运动目标分割方法。分割试验显示了该运动目标分割方法的有效性和可行性。提出融合梯度算子和子区合并技术进行区域分割的方法,子区合并技术能够在一定程度上防止两个独立的区域被错误的合并成一个区域, 这种区域分割方法和常用的Region growing算法的对比分割试验显示该方法对灰度变化不均匀的区域进行分割的效果优于Region growing算法。