采用改进OTSU法的焊前焊缝图像分割

图像分割是图像理解与分析的基础，在众多的图像分割方法中，阈值法计算简单，具有较高的运算效率，是图像分割中广泛采用的方法，选取适当的阈值是阈值法的关键。OTSU法（最大类间方差法）被认为是阈值自动选取方法的最优方法之一，由于焊缝图像常出现大面积的灰度不均匀，OTSU方法不能有效地分割出焊缝间隙，在充分分析焊缝图像以及OTSU方法的基础上，提出一种改造的自适应阈值选取方法，实验证明该方法具有较强的自适应性；能有效地分割焊缝图像。     

基于有监督过渡区的焊缝X射线图像分割

针对X射线焊缝检测图像中存在大量背景冗余信息,焊缝和缺陷难于准确检测提取的问题,提出一种基于先验知识的有监督过渡区域提取及阈值分割方法.根据焊接图像本身的特点,通过先验知识对样本图像进行训练,确定某个区间来估算图像过渡区域的灰度范围,按照模糊子集理论,给出一种新的加权算子来描述局部窗口内灰度级的变化,从而能充分考虑到局部窗口内灰度级变化的频率和幅度,通过计算过渡区域像素的灰度均值,将其作为阈值对图像进行分割.结果表明,该方法能准确地将目标缺陷从焊缝X射线图像中分割出来,具有良好的适应性.     

基于低秩矩阵的自适应边缘检测算法

针对传统边缘检测算法处理含噪图像存在边缘模糊、缺失等问题,为提高算法的抗噪性与边缘完整性,提出了一种基于低秩矩阵的自适应边缘检测算法。首先使用低秩矩阵理论将图像中稀疏噪声矩阵分离,在去除噪声的同时能完好保留图像边缘,再根据图像灰度采用迭代循环的方法进行阈值分割选取,最终提取出连续完整的边缘。实验结果表明,使用该算法在混合噪声情况下具有较好的抗噪声能力与算法鲁棒性,提高了边缘信息的完整性,在视觉测量的应用取得了较好的效果。     

基于图像特征识别的部件缺陷无损检测方法(英文)

图像处理在金属部件内缺陷无损识别检测中有重要应用,但在原始图像辨识处理中至今仍存在如边缘不清晰等诸多问题。为消除传统图像辨识中的边缘不连续,伪边缘、过分割,提出了一种基于模糊形态学的图像几何特征辨识算法。该算法基于模糊形态学辨识结构元素特征,分析各元素间的相互关系,对经预处理后的图像确定隶属度函数参数,采用最优阈值自动识别方法确定图像最佳分割阈值,以最佳阈值和路径代价函数为约束条件,缩小路径搜索范围,提高算法执行速度,借助分水岭算法重现图像边缘,辨识出图像的几何特征。最后以一种特殊的图像几何特征识别为例进行了数字仿真。仿真图像显示,经处理后的图像边缘连续,无伪边缘和过分割现象,图像更加平滑,柔和性更好。研究结果表明,该方法是可行和有效的。     

应用于刹车盘复杂背景去除的改进Grab Cut分割算法北大核心

针对无序分拣过程中车间光照不均导致的分割结果不准确问题,提出一种改进的Grab Cut图像分割算法。该算法采用自适应中值滤波去除图像表面噪声;通过限定对比度自适应直方图均衡化提升图像整体亮度,增强对比度;进一步使用Laplacian算子对刹车盘区域进行锐化处理;在此基础上对刹车盘图像复杂背景进行去除;最后通过仿真实验对比分割效果、PSNR、误分割率、分割准确性和运行时间来评价算法模型。实验结果表明:提出的改进Grab Cut分割算法相较于原始算法能有效降低光照不均对刹车盘复杂图像背景去除的影响,使分割准确率提高了12.5%,分割结果与实际刹车盘模型相比误差小,为刹车盘图像复杂背景去除提供参考。     

高温轴类大锻件的图像分割算法研究

采用非接触CCD图像测量技术对高温大锻件进行测量时,需要从采集的图像中分割出大锻件目标图像。对高温物体成像特性进行了研究,并对高温锻件的辐射出射度与成像灰度的关系进行了讨论;采用线扫描方法,获得了850～1000℃高温锻件倒棱滚圆过程中图像的RGB基色分布规律,发现了背景和锻件目标区域红色灰度均值和蓝色灰度均值的相关性。在此基础上,提出了一种基于动态相对阈值和动态绝对阈值的图像分割算法。实验表明,此方法能对图像中的锻件目标实现精确的分割。     

水下焊缝自动跟踪路径的识别

为满足水下焊缝自动跟踪的需要,设计了一个视觉系统。该系统采用卤钨灯作辅助光源照射焊接电弧前方一定距离处的待焊焊缝．配合复合滤光片进行滤光,能拍摄到较为清晰的焊缝图像。提出了一个基于边缘邻域平均值的算子,用于图像的边缘增强。运用改进的遗传算法计算图像类间方差,求出最佳阈值进行图像边缘分割,能较好地保留图像弱边缘．有效地减少计算时间。对分割后的焊缝图像,提出一种基于待焊焊缝宽度等特征的识别方法,能克服焊接弧光、飞溅、水流、气泡等干扰,识别水下待焊焊缝．准确地获取待焊焊缝中心线．为进一步实现水下焊接的自动化打下了基础。     

基于DNA算法的铁路机车闸瓦检测方法研究

针对目前国内铁路机车闸瓦安装复杂,周边部件多,难以准确定位闸瓦位置,实现其磨损状态自动检测的情况,提出了一种基于DNA计算的机车闸瓦图像检测新方法,首先构建了一套闸瓦图像的采集系统,当机车运行到特定位置时,系统能够自动采集闸瓦图像,将其保存至计算机硬盘。在此基础上,对采集到的闸瓦图像进行中值滤波及灰度增强,并研究了一种基于DNA计算的图像阈值分割算法。与传统的ostu阈值法相比,新算法能准确定位闸瓦,有效获取闸瓦区域的阈值,分割闸瓦信息。对分割后的闸瓦图像进行数学形态学处理,去除闸瓦周边的孤立点,并采用sobel边缘检测法提取到了较为理想的闸瓦边缘,为实现闸瓦的自动检测奠定了基础。     

基于机器视觉的线缆表面缺陷快速检测算法研究

利用机器视觉技术检测线缆表面缺陷时,检测时间长、漏检率高。为此,提出一种基于机器视觉的线缆表面缺陷快速检测算法。通过引入CV-Kmeans区域分类算法建立自适应滤波窗口改进高斯滤波算法,在此基础上建立自适应模板,然后计算原图像与模板的Pearson(皮尔逊)相关系数快速判断图像是否含有缺陷。对含有缺陷的图像进行模板与原图差分,最后对差分所得到的图像用自适应阈值分割法提取缺陷。实验表明,算法可有效识别缺陷并减少检测时间,漏检率为3.22%,满足线缆生产需求。     

Learning in presence of class imbalance and class overlapping by using one-class SVM and undersampling technique

ABSTRACT

The class imbalance problem engraves the traditional learning models by degrading performance and yielding erroneous outcomes. It is the scenario where one of the class representation is over-shadowed by other classes in a data space. Presence of class imbalance can cause a grave difficulty as misclassification cost of minority class tends to be very high. Presence of overlapping cases along with the case of imbalanced data, can lead to create grim situation for effective learning. In this study, an in-depth analysis of the effects of class imbalance and class overlapping in conventional learning models has been presented. A data level approach is adapted with one-class SVM-based anomaly detection to detect the cases of data overlapping while an adapted Tomek-link undersampling algorithm is defined to treat both overlapped and imbalanced cases. The proposed model evolves to eliminate borderline, redundant and overlapping cases with the account of Tomek-link pair and sparse neighbourhood. The proposed method has been evaluated with six state-of-the-art models for seven binary and two multiclass datasets, with respect to three standard learning models. The proposed model has been evaluated with cost-sensitive learning and extreme learning based approaches for imbalanced class learning. The proficiency of the proposed method over state-of-the-art models is established through experimental analyses.     

Probabilistic region growing method for improving magnetic resonance image segmentation

In this paper, we propose a new region growing algorithm called ‘probabilistic region growing (PRG)’ which could improve the magnetic resonance image (MRI) segmentation. The proposed approach includes a threshold based on estimating the probability of pixel intensities of a given image. This threshold uses a homogeneity criterion which is obtained automatically from characteristics of the regions. The homogeneity criterion will be calculated for each pixel as well as the probability of pixel value. The proposed PRG algorithm selects the pixels sequentially in a random walk starting at the seed point, and the homogeneity criterion is updated continuously. The proposed PRG algorithm is applied to the challenging applications: grey matter/white matter segmentation in MRI data sets. The experimental results compared with other segmentation techniques show that the proposed PRG method produces more accurate and stable results.     

基于聚类的埋弧焊X射线焊缝图像缺陷分割算法及缺陷模型

针对埋弧焊X射线焊缝图像的噪声强、弱对比度特点和常规图像分割算法成功率低的现状,提出将缺陷视为噪声,利用密度聚类方法进行缺陷分割.在进行图像聚类时,提出图像灰度密度的概念,方便对焊缝图像的分割.通过对现场100张焊缝图像的试验表明,所提方法大幅度地提高了缺陷分割的成功率,将分割成功率提高至95%.在聚类分割算法基础上,通过试验给出一种新的高维空间缺陷数学模型,该模型综合考虑了缺陷形式复杂性等特征.通过试验在高维空间对模型予以验证,并结合所提聚类算法给出了覆盖率曲线.     

A weighted pattern matching approach for classification of imbalanced data with a fireworks-based algorithm for feature selection

ABSTRACT

Learning a classifier from imbalanced data is a challenging problem in Machine learning. A dataset is said to be imbalanced when the number of instances belonging to one class is much less than the number of instances belonging to the other class. Classifiers that proves efficient on standard data fail when the data is imbalanced as they are over trained by the majority class instances. Since class imbalance is a common characteristic of real-world data, the need for better classifiers becomes essential. This paper proposes a novel instance-based classification algorithm called Weighted Pattern Matching based Classification (PMC+) for classifying imbalanced data. PMC+ classifies unlabelled instances by computing the absolute difference between the feature values of the instances in the dataset and the unlabelled instance. PMC+ employs a simple classification procedure with weights and shows reasonably good performance. To improve the performance of PMC+, Fireworks based Feature and Weight Selection algorithm based on the idea of PMC+ has been proposed. PMC+ is evaluated on 44 binary imbalanced datasets and 15 multiclass imbalanced datasets. Although PMC+ does not employ a resampling or cost-sensitive method, experiments show that PMC+ is effective for classification of imbalanced data. The results of the experiments were validated using various non-parametric statistical tests.     

Damage diagnostics on a welded zone of a steel truss member using an active sensing network system

In this paper, a sensor network system based on an active sensing scheme is introduced to identify cracks, which may occur at a welded zone of a steel truss member. The active sensing network system offers special potential for real world applications, as it is light, cheap, and useful as a built-in system. Four pairs of pitch–catch Lamb wave signals are utilized from the active sensing network system. In order to extract damage-sensitive features from the dispersive Lamb waves, a robust wavelet transform is applied to the original response signals. Peak values in the wavelet coefficients corresponding to the A₀ Lamb mode are only considered for application to the damage index. The root-mean-square change of the peak values due to damage is proposed as a damage index. In addition, a least-squares curve-fitting algorithm is applied to the damage indices in order to obtain a practical damage indicator with a threshold value that presents the damage tolerance. Finally, damage localization is carried out by investigating the change rates of the damage index according to each damage step. The applicability of the proposed methods has been demonstrated by an experimental study.     

区域生长算法的改进及其在异物检测中的应用

提出一种基于区域生长的图像分割算法,并达到异物识别的目的。该算法根据不同X射线图像直方图的特征,自动选取出所需要的种子点,并且通过对已进行过区域生长的部分进行概率统计,得出合适的阈值,进行种子区域生长。相对于一般的根据每幅图像手动选取种子点以及闽值的种子区域生长法（SRG）,该算法能够快速有效地进行图像分割,异物识别率高。     

基于FGT-FBP重构算法的焊接缺陷检测

针对焊接过程产生的缺陷,提出一种磁光成像传感的模糊灰度变换和滤波反投影(FGT-FBP)重构检测方法. 研究焊接缺陷的几何特征,通过分析裂纹和未熔合两种不同焊接缺陷在交变磁场励磁下的磁光成像特征,设计模糊规则,对磁光图像进行模糊灰度变换. 增强磁光图像对比度,使焊接缺陷形态趋势可视化,实现描述磁光成像焊接缺陷细节的无参考型图像评估方法. 对FGT处理的焊接缺陷磁光图进行旋转投影,并经过快速傅里叶变换和改进的滤波器进行滤波去噪,消除伪影后进行反投影变换实现焊接缺陷图像的重构. 利用滤波反投影重构算法进行去噪,可有效突出焊接缺陷特征. 最后结合阈值分割和边缘检测实现焊接缺陷检测. 结果表明,该方法能较准确检测裂纹和未熔合两种焊接缺陷.     

基于激光视觉的钢结构焊缝图像处理系统

针对钢结构件品种多、批量小,焊缝形状位置一致性差,机器人重复定位过程复杂等缺点,设计了一种基于激光视觉的钢结构焊缝图像处理系统. 运用CCD工业相机和激光器,采集带有激光条带的焊缝图像,分别利用中值滤波柔化噪音,Otsu算法自适应阈值分割,开操作和形态学处理相结合去除图像中除目标像素外的小连通区域,提取激光条带的中心线,最终利用Hough变换对中心线直线拟合,得到特征点位置,并通过骨支架试验验证该技术的可行性. 结果表明,该方法可快速准确地检测到焊缝特征点,满足实际要求.     

焊缝位置识别的图像处理方法设计

在基于视觉的自动焊接中，由于焊缝图像是复杂多变的，要准确得到焊缝位置选择合理高效的处理算法是非常重要的。针对这一问题为焊缝图像提出了一系列处理步骤，它包括中值滤波、自适应阈值二值化、孤点滤波、边缘检测，焊缝位置搜索五步，其中详细叙述了重要的自适应阈值二值化与孤点滤波算法。在每一步处理中都用了四幅完全不同的焊缝图像做了观察和对比，结果显示所选算法产生较好的处理效果。     

一种基于视觉的干电池检测方法

提出一种基于视觉的干电池检测方法.采用自适应的图像分割方法实现锌桶、内外层胶、电解质和碳棒的图像分割;根据分割后的图像,分别采用圆拟合来进行尺寸计算;通过计算锌桶的厚度和变形、内外层胶的厚度、电解质的厚度及碳棒中心相对于锌桶中心的偏移量来检测各项缺陷.实验结果表明:该干电池检测方法具有稳定、可靠和精度高等特点,达到了快速、有效地实现干电池尺寸测量和缺陷检测的目的.     

基于模糊聚类算法的孕镶金刚石钻头出刃图像分割

本文针对孕镶金刚石钻头唇面彩色图像的特征,采用模糊聚类方法对图像中的色彩进行了聚类分析,以提取出刃的金刚石图像。在图像预处理的基础上,对比了两种图像色彩描述空间对聚类分析的影响,并把模糊聚类分析结果与最大类间方差阈值分割法的分析结果进行了比较。结果表明：模糊聚类方法可对孕镶金刚石唇面的颜色进行有效分类,并准确提取出刃的金刚石图像;用RGB的线性变换量描述金刚石唇面图像,比用Lab色彩空间描述图像,更能得到理想的分割效果;对于孕镶金刚石唇面图像而言,最大类间方差阈值分割法难以区分金刚石颗粒和犁沟,分割效果不如模糊聚类法。