基于机器视觉的PCB裸板缺陷自动检测方法

提出了通过比较标准图像与待测图像差异并分析差异区域边界进行印刷线路板(PCB)缺陷检测与识别的算法。在同一位置采集多幅标准PCB图像并计算其灰度平均值从而得到标准图,将待测PCB图与其进行对比。首先使用限定区域Hough变换快速检测出图像中相互垂直相交的细短标志线,将线段的交点作为特征点并计算其坐标,进而对标准图与待测图进行仿射变换配准,差影计算后,再通过二值化、形态学处理等去除伪缺陷,即可获取缺陷区域位置。在此基础之上,对处理过的差影图进行膨胀处理,通过边界检测获取各个缺陷区域闭合轮廓各点坐标。分析各个轮廓坐标对应阈值分割后的配准待测图中点的像素值,并结合缺陷是缺料缺陷还是多料缺陷识别出缺陷类型。对合格的和有缺陷的PCB图各200幅进行算法测试,检测准确率为98.3%,基本能够稳定检测出常规缺陷。     

采用Gerber文档的印刷电路板表观检测

对印刷电路板(PCB)进行表观检测时,传统标准板的图像建立是利用PCB图像自身的特征进行配准和分层的,故检测精度不高.本文从PCB表观检测的实际需求出发,提出了新的检测系统.该检测系统引入解析Gerber文档对PCB光电图像进行分层处理,利用形态学的方法自动修正解析后的Gerber文档,建立精确的标准板.根据主分量分析提取彩色图像频带丰富的信息,依据检测缺陷的尺寸大小设置各层模板及检测阈值,实现局部针对性检测,提高检测精度.实验结果表明,与传统的基于颜色分区域方法相比,基于Gerber的方法不仅提高了检测精度,且较大幅度地提高了自动光学检测系统的检测效率,其微小缺陷检测率高达95.1％,25 cm×22 em电路板检测时间仅需1.09 s,满足了在线检测对速度的要求.     

基于无损检测的高分辨率PCB板焊点缺陷检测系统

为了能快速、准确地对BGA封装器件的PCB板上的焊点进行缺陷检测,设计了高分辨率X-射线无损检测的缺陷检测系统.给出了系统的基本工作原理和硬件结构,采用等比例成像的方法求解了获得最高分辨率的距离信息.分析了系统可能存在的噪声源,并设计了去噪算法用于提高图像信噪比.试验采用HAWK-180XI型X-射线源、高速图像采集卡和UNIQ-2000型CCD相机等对BGA封装的PCB板缺陷进行检测,结果显示:系统可以快速有效地获得被测PCB板的图像信息,并给出缺陷的位置、尺寸等特征信息,满足设计要求.     

基于改进模板匹配及像素相加法的芯片极性二级检测方法

针对PCB板缺陷检测中的芯片极性检测问题,文中提出一种结合感兴趣区域提取,改进模板匹配以及像素相加法的芯片极性二级检测方法。该方法首先通过先验知识提取感兴趣区域,并提出改进模板匹配实现对芯片位置快速准确地定位,随后引入直方图匹配及中值滤波对芯片图像进行预处理,最后提出基于像素相加法的二级检测方法实现二值化芯片图像的极性判断。实验结果表明,文中提出的方法在芯片定位及极性检测方面都有更高的准确性。     

基于加权SSIM算法的PCB元件缺陷检测

提出了一种自动光学检测方法,通过将传统的SSIM算法与元件的权重相结合的方法来检测PCB元件缺陷。该方法基于图像内容生成权重图,与SSIM矩阵相乘,它可以有效地增强平滑区域信息并消除高频区域的干扰。该系统不需要严格照明条件,对相机性能要求不高。实验结果表明,该方法在PCB缺陷检测精度方面,特别是对位置变化较大的插件元件的检测优于传统的SSIM方法。将有助于开发低成本和自动化的缺陷检测系统。     

陶瓷PCB基板缺陷检测设备结构设计与改进

根据一种陶瓷PCB基板表面缺陷视觉检测的实际需求,对比分析了多种物料输送方案,最终设计制造了一款自动化检测设备,实现了PCB板件从料箱中自动取放并通过视觉检测装置完成拍照取像,并实现缺陷标记功能。设备硬件主要由自动上料模块、板件传送模块、视觉检测模块、点胶打标模块、自动下料模块组成,电气控制系统采用PLC搭建。在实际测试使用中发现了板件吸附压紧不平和打标点胶针头堵墨等问题,对板件载物台和点胶针头进行了设计改进,并通过测试验证证明,基本满足使用需求。     

一种基于混沌优化算法的PCB板元件检测方法

先进电子制造生产中经常要对PCB板元件进行检测与识别,介绍了一种基于图像模板匹配算法的PCB板元件自动快速检测方法.从检测速度和准确度出发,首先提出了一种图像相似性度量参数指标,并提出一种利用并行混沌算法融合单纯形的算法,来优化搜索图像相似性,给出了算法实现的全过程.用实际拍摄的PCB板元件进行性能测试,验证了该优化算法能提高检测速度.     

基于虚拟仪器的机器视觉在PCB元器件检测中的应用

PCB板的检测是电子设备制造过程中的重要环节,它是产品质量和性能达标的重要保障.为了实现生产过程中缺陷检测的自动化,研究了用机器视觉检测技术检测PCB元器件缺陷的方法.本文使用LaDVIEW、NI Vision Assistant和Vision Builder对所采集的PCB图像进行了处理且做出相应分析.通过实验证明,所讨论的方法对缺陷检测能够达到满意结果.     

高精度贴片机视觉系统图像预处理算法研究

针对高精度自动贴片机的视觉系统图像预处理算法进行了研究,提出了针对贴片机PCB板标记点及元件图像处理的预处理方法.开发了针对视觉定位系统的图像识别软件,并用PCB板图像及元件图像进行实验验证.实验结果表明,该预处理算法能够有效地分割原始图像目标区及背景区、排除干扰噪声、增强图像特征,为贴片机进一步的图像识别及定位提供了有利条件.     

基于直方图数据拟合的PCB板嵌孔识别研究

快速精准地识别PCB板上感兴趣区域的位置,是图像处理过程中衡量算法有效性的重要指标。在图像处理的前期,通过分析同一背景条件下灰度曲线的变化趋势,确定光照不均匀对于PCB板感兴趣区域的影响,提出了运用同态滤波处理降低图像灰度变化的动态范围,从而加强感兴趣区域中目标和背景的对比度。基于现阶段相关PCB板的识别分割算法,针对研究对象PCB板实际感兴趣区域的灰度分布,探讨了全局阈值分割方法的优势。在此基础上,为了更精确的图像分割效果,提出了一种基于灰度直方图数据拟合的阈值分割方法。根据不同的阈值分割算法对图像进行处理,通过比较分析,结果表明本文提出的算法能够更加快速精确地分割出图像的感兴趣区域。     

Defect Detection of Gold-Plated Surfaces on PCBs Using Entropy Measures

Connector fingers are metallic pads at the edge of a printed circuit board (PCB). They must be inspected after plating to ensure that an adequate coating of gold has been applied. The gold-plated surface is not uniform, but produces a homogeneous texture in the image. In this paper, we propose two entropy measures of chromatic and structural regularities for the automatic defect inspection of gold-plated fingers (edge connectors) on PCBs. One entropy measure uses two chromatic features derived from the CIELUV colour space to detect colour anomalies, and the other measure uses edge angles to detect structural defects on gold-plated surfaces. Experimental results have shown that the proposed method is effective and efficient for detecting various defects such as pinholes, copper exposure, and nicks and roughness on gold-plated surfaces.     

基于梯度方向信息熵的印刷电路板缺陷检测

针对印刷电路板裸板缺陷在线视觉检测,提出了一种适用于电路板彩色图像的缺陷检测算法。该算法主要通过分析缺陷区域边界像素的梯度方向信息获得对应的典型图像特征,具体由滤波去噪、目标分割和特征提取三部分组成。为减弱环境光干扰同时保证边缘细节的清晰,首先在CIE Lab色彩空间对图像进行双边滤波,然后利用该色彩空间的均匀性分割出需要检测的目标区域,最后设计了邻域梯度方向信息熵这一描述子用于提取缺陷特征和构造特征向量,利用支持向量机对缺陷进行识别。实验结果表明:所提算法能够对印刷电路板裸板存在的短路、断路、孔洞、余铜、划痕等常见缺陷进行快速精确的定位,能够满足生产过程中的实时检测要求。     

内置无铅锡膏印刷机的检测算法研究

针对PCB锡膏印刷中常见的偏移、桥接、少锡、多锡等缺陷,提出了一种可集成于锡膏印刷机的机器视觉锡膏检测算法。该算法通过对锡膏印刷特征的建模、锡膏的定位、区域特征的提取,实现了锡膏印刷缺陷的检测。实验结果表明,该算法能够有效地识别常见的印刷缺陷,并且速度上可满足在线检测要求。     

Surface defect detection in tiling Industries using digital image processing methods: Analysis and evaluation

Ceramic and tile industries should indispensably include a grading stage to quantify the quality of products. Actually, human control systems are often used for grading purposes. An automatic grading system is essential to enhance the quality control and marketing of the products. Since there generally exist six different types of defects originating from various stages of tile manufacturing lines with distinct textures and morphologies, many image processing techniques have been proposed for defect detection. In this paper, a survey has been made on the pattern recognition and image processing algorithms which have been used to detect surface defects. Each method appears to be limited for detecting some subgroup of defects. The detection techniques may be divided into three main groups: statistical pattern recognition, feature vector extraction and texture/image classification. The methods such as wavelet transform, filtering, morphology and contourlet transform are more effective for pre-processing tasks. Others including statistical methods, neural networks and model-based algorithms can be applied to extract the surface defects. Although, statistical methods are often appropriate for identification of large defects such as Spots, but techniques such as wavelet processing provide an acceptable response for detection of small defects such as Pinhole. A thorough survey is made in this paper on the existing algorithms in each subgroup. Also, the evaluation parameters are discussed including supervised and unsupervised parameters. Using various performance parameters, different defect detection algorithms are compared and evaluated.     

锥束CT图像中的印刷电路板导线自动检测方法

针对印刷电路板(PCB)的CT图像存在灰度不均匀、导线形状多变等特点导致的导线难以有效检测的问题,提出了一种基于超像素分割的PCB导线自动检测方法。该方法使用基于引导滤波的类顶帽变换对图像预处理,提高不同类别区域的类间差异,改善后续的超像素分割结果;然后选择graph-based超像素分割算法对导线定位;最后,采用导线几何形状、灰度分布等特征判断识别导线区域,实现导线检测。对存在灰度不均匀、多条导线、多尺度的PCB CT图像进行了实际实验。结果显示:该算法取得了较好的导线检测结果,在实验测试图像上检测率达到了90%以上,基本满足导线自动检测对精度和抗干扰能力的要求,具有较高的应用价值。     

Logistic regression tree applied to classify PCB golden finger defects

Automatic inspection and classification of printed circuit board (PCB) defects remains a problem in the Integrated Circuit (IC) industry. In a small volume, large production variety environment, some of the widely used defects classification tools are the Bayes classifier, the linear discriminant function (LDF) classifier, the minimum distance classifier, and the K-nearest neighbour (K-NN) classifier. These classifiers all have shortcomings and their applications are limited. This study proposes the logistic regression tree as classifier where each node implements a logistic regression model to make a binary split, and draws a comparison with other classifiers. This experiment uses the Red-Green-Blue (RGB) values of an image with PCB golden fingers, as opposed to some features extracted from the image. The golden fingers defects considered in this study are scuffing, blotted tin, exposed nickel, and unplating. The result of this experiment shows that the logistic regression tree has an accuracy of 89.33%, while other classifiers can only achieve 81.67% to 87.17%. Furthermore, the decision flexibility and the result stability show that the logistic regression tree is an excellent choice as a classifier. This revised version was published online in October 2004 with a correction to the issue number.     

A hybrid defect detection for in-tray semiconductor chip

The requirements for high-speed and high-precision defect inspection in semiconductor chip are growing rapidly because of the complicated surface in semiconductor chip. Due to manufacturing tolerance of IC tray, the misalignment from the chip positioning shift and rotation are always presented for the application of in-tray inspection. In the beginning, this paper focuses on compensating the positioning shift and rotation of in-tray chip by using the proposed image alignment algorithm before the defect detection. After applying the process of image alignment, a hybrid approach of defect detection is applied to detect the defects of in-tray chip. Furthermore, this hybrid approach simultaneously detects the defects based on its surface by the following two categories: (1) the complicated surface in the circuit and (2) the primitive surface on the bump. As mentioned above, the image alignment strategy and the adaptive image difference method are applied in the detection of complicated surface, and the design-rule strategy is adapted to detect the defects on bumps. Finally, the experimental results show that the proposed image alignment strategy and hybrid approach can accurately and rapidly inspect the defects of in-tray chip. This approach is superior to the traditional template matching in defect detection. In addition, the computational complexity can be efficiently reduced by the proposed hybrid strategy.     

LabVIEW Vision在汽车发动机进气管检测系统中的应用

针对汽车发动机进气管中存在杂质及缺陷难以检测的现状,提出了以机器视觉为基础,以LabVIEW的Vision and Motion模块及其附属可视化软件Vision Assistant获取图像信息的检测方法。通过对图像进行预处理、形态学处理、图像分割、高级形态学处理等建立起一个完整的汽车发动机进气管检测系统。实践表明,该检测方法操作合理,检测方便,实用性强,可视化效果好,完全满足检测技术要求。     

一种SMT生产缺陷自动检测系统的设计与实现

为了控制PCB成品质量,设计和实现了对SMT生产缺陷的自动检测。采用定位、摄像和图像处理等技术,精确检测和标识PCB产品的缺陷。系统运行可靠,降低了SMT生产成本。     

焊接缺陷磁光成像动态检测与识别

为了实现焊接缺陷的自动检测,研究一种交变磁场激励下焊缝表面及亚表面缺陷的磁光成像动态无损检测方法。分析了基于法拉第磁致旋光效应的焊接缺陷磁光成像机理,并结合交变磁场原理推导出励磁变化与动态磁光成像的关系。探索低碳钢板的亚表面焊缝磁光成像特征试验,验证了所提方法可用于检测焊缝亚表面的未熔合缺陷。最后对高强钢焊缝特征的动态磁光图像进行分析,采用主成分分析法和支持向量机(PCA-SVM)模式识别方法建立了焊接缺陷分类模型。试验结果表明,所提方法可以识别高强钢焊件中的焊缝特征(未熔透、裂纹、凹坑和无缺陷),缺陷分类模型的整体识别率达到92.6%,能够实现焊缝表面及亚表面缺陷的自动检测。