Surface roughness classification using image processing

Surface roughness is an important factor in determining the satisfactory functioning of the machined components. Conventionally the surface roughness measurement is done with a stylus instrument. Since this measurement process is intrusive and is of contact type, it is not suitable for online measurements. There is a growing need for a reliable, online and non-contact method for surface measurements. Over the last few years, advances in image processing techniques have provided a basis for developing image-based surface roughness measuring techniques. Based upon the vision system, novel methods used for human identification in biometrics are used in the present work for characterization of machined surfaces. The Euclidean and Hamming distances of the surface images are used for surface recognition. Using a CCD camera and polychromatic light source, low-incident-angle images of machined surfaces with different surface roughness values were captured. A signal vector was generated from image pixel intensity and was processed using MATLAB software. A database of reference images with known surface roughness values was established. The Euclidean and Hamming distances between any new test surface and the reference images in the database were used to predict the surface roughness of the test surface.     

Efficient work measurement system of manufacturing cells using speech recognition and digital image processing technology

Work measurement methods previously proposed require considerable time and effort by time study analysts because they have to measure the required time through direct observations. In this study, however, we propose a method which efficiently measures the standard times without involving human analysts by using speech recognition and digital image processing techniques. First, we implement a prototype system which can acquire the status of manufacturing cells through a speech recognition system. Second, using image processing, we suggest a method which consists of two main steps: motion representation and cycle segmentation. In the motion representation step, we first detect the motion of any object distinct from its background by differencing two consecutive images separated by a constant time interval. The images thus obtained then pass through an edge detector filter. Finally, the mean values of coordinates of significant pixels of the edge image are obtained. Through these processes, the motions of the observed worker are represented by two time series of data of worker location in horizontal and vertical axes. In the cycle segmentation step, we extract the frames which have maximum or minimum coordinates in one cycle, store them in a stack, and calculate each cycle time using these frames. In this step we also consider methods for detecting work delays due to unexpected events such as an operator’s movement out of the work area, or interruptions. To conclude, the experimental results show that the proposed method is very cost-effective and useful for measuring time standards for various work environments.     

注塑产品在线检测的图像处理系统设计与研究

针对注塑产品检测中需要精密的机械装置实现定位的问题,对运用图像处理系统来完成其缺陷检测时所需的定位、配准及判断等方面进行了研究,对进行缺陷检测的图像处理系统流程进行了归纳,提出了一种通过对比图像的直线参数,并结合形心位置获得用于矫正待检图像位置的旋转量,再通过Hough变换测得的直线端点参数获得矫正待检图像的平移量,并结合基于FFT的相关运算来辅助确认平移量,最终根据经腐蚀运算的差影图像中各连通区域的面积判断产品是否存在缺陷的图像处理软件系统。利用Matlab对该系统进行了实现,并使用多种待检图像与模板图像进行对比测试。研究结果表明,该系统兼顾实时性和精确性,所设计的图像处理软件系统能够在廉价的低精度机械定位装置上实现注塑产品的在线检测。     

刀具磨损检测中的图像处理技术研究现状及展望

针对刀具磨损检测在图像处理技术中的发展现状总结,并对刀具磨损检测在图像处理技术应用趋势下做出展望。首先,对刀具的磨损检测系统简单的介绍和总结;其次,对检测后的图像预处理、磨损区域提取及边缘检测、磨损状态识别技术的相关内容进行详细讨论。最后,结合目前计算机视觉、人工智能等新形势下对刀具磨损检测在图像处理技术中做出展望。     

面向机柜表面缺陷检测的不均匀光照和低亮度图像增强方法

光照条件是大尺寸机柜表面缺陷检测的重要影响因素。当光照分布不均匀或光照强度不足时,采集得到的机柜表面图像质量低,造成缺陷检测误差。为此,提出一种融合卡通纹理分解和最优双曲正切曲线的图像增强方法。首先,采用导向滤波将机柜表面图像分解为卡通图和纹理图,利用高斯尺度空间理论建立光照模型,实现不均匀光照去除;其次,研究图像的双曲正切曲线性质,通过图像加权拉伸实现低亮度图像增强;最后,采用对比度、亮度和灰度方差乘积对图像增强效果进行评价,同时对增强前和增强后的图像进行缺陷检测,进行对比分析验证。实验结果表明,该方法能实现光照不均且低亮度的机柜表面图像增强,机柜表面缺陷检测的准确率显著提升,召回率提高了29%,F值提高了21%。     

BGA焊点空洞缺陷的数字形态学检测

空洞缺陷是BGA焊接缺陷中比较常见的一种, 主要由回流焊时产生的气体没有及时排出而导致. X射线无损检测技术可以使空洞缺陷在焊球图像上显示为白色区域供技术人员查看, 但在噪声、不均匀照射、存在与缺陷类似目标的干扰下如何准确地自动提取缺陷一直是个难题. 提出使用Otsu算法分割焊球, 使用数学形态学中的开闭运算、 顶帽变换提取空洞缺陷的技术方案, 实现每个焊点空洞缺陷的准确提取和自动分析. 实验结果表明, 提出的技术方案鲁棒性强, 可应用于BGA焊点的空洞缺陷检测.     

滚动轴承保持架缺陷的图像处理及模式识别方法研究

轻系列滚动轴承保持架由于兜孔直径小、两半保持架之间钉孔距离相对较大等因素导致在铆压过程中易出现变形,造成铆压歪斜缺陷。为此,本文提出了基于图像纹理特征的模式识别方法用于保持架歪斜缺陷的准确识别。首先,改进了轴承图像归一化展开算法,实现了轴承图像展开起点的自动优化选择以避免误分割保持架、铆钉和滚动体;其次,设计了轴承图像保持架区域定位分割算法,准确分离出7个保持架区域;最后,分别提取保持架区域的Hu矩和旋转不变均匀局部二值模式(LBPrPiu,2R)作为纹理特征,并结合PCA降维方法构建轴承保持架缺陷识别的SVM分类模型。结果表明,基于Hu矩和LBPrPiu2,R的SVM模型的正确识别率分别为85%和100%。因此,轴承LBPrPiu2,R特征结合SVM模型对轴承保持架歪斜缺陷具有较好的识别效果。该方法有望为滚动球轴承保持架铆压工艺缺陷的自动识别提供参考。     

硅钢酸洗-冷连轧系统中表面缺陷识别方法研究

针对硅钢酸洗-冷连轧生产过程中钢带表面缺陷的特点,在提取钢带图像低层属性特征的基础上,采用决策树、SVM、BP神经网络等不同的模式识别方法对钢带表面缺陷进行分类研究,试验过程包含训练集与测试集的收集、特征提取、机器学习与分类、结果分析.该研究以提高硅钢冷轧生产过程的自动化水平为目标,依据试验结果提出缺陷识别的优化方法,并应用于武钢硅钢冷轧生产线,提高了自动化水平.     

基于视觉的输电线路金具锈蚀缺陷检测方法研究进展

输电线路金具的表面锈蚀作为常见的缺陷类型,是危害输电线路安全运行的重要隐患之一,如何快速、准确地发现锈蚀 的金具设备并进行修复是线路巡检运维工作亟待解决的问题。 本文综述了近十年来基于视觉的输电线路金具锈蚀缺陷检测方 法的研究进展。 首先简述了基于传统图像处理的金具锈蚀缺陷检测流程;然后按照基于传统图像处理、深度学习方法概述了金 具设备锈蚀缺陷检测,重点阐述了基于深度卷积神经网络的目标检测和语义分割算法在输电线路金具锈蚀缺陷检测中的应用; 随后介绍了基于深度学习的金具锈蚀缺陷检测自建数据集以及性能评价指标;最后指出了基于深度学习的输电线路金具锈蚀 缺陷检测方法目前存在的问题,并对未来研究工作进行了展望。     

基于图象处理测量的轮对轮缘形状的研究

本文提出一种善于数字图象处理的轮对故障检测技术。该技术采用半导体激光器为光源通过高精度CCD传感器获取轮对踏面的图象．并将图象进行二值化和细化处理,分析踏面参数与系统参数的几何关系．从而得到踏面的几何参数值。现场检测的结果表明：本方法是可行的,具有测量精度高和稳定性好的特点,测量精度可达0.1mm。