Development of an optical inspection platform for surface defect detection in touch panel glass

An optical inspection platform combining parallel image processing with high resolution opto-mechanical module was developed for defect inspection of touch panel glass. Dark field images were acquired using a 12288-pixel line CCD camera with 3.5 µm per pixel resolution and 12 kHz line rate. Key features of the glass surface were analyzed by parallel image processing on combined CPU and GPU platforms. Defect inspection of touch panel glass, which provided 386 megapixel image data per sample, was completed in roughly 5 seconds. High detection rate of surface scratches on the touch panel glass was realized with minimum defects size of about 10 µm after inspection. The implementation of a custom illumination source significantly improved the scattering efficiency on the surface, therefore enhancing the contrast in the acquired images and overall performance of the inspection system.     

基于智能图像识别的烟盒包装质量快速检测系统的研究

提出一种基于智能图像识别技术的烟盒包装瑕疵检测方法,将图像处理为灰度值矩阵后,通过感兴趣区域和 Sobel 算子边框查找法进行瑕疵快速识别。提出一种基于机器学习和 SVM s 模式识别的分级算法,实现包装瑕疵的快速分类。建立了盒装香烟包装质量检测系统模型,验证所提算法具有正确识别率高和误判率合理等优点,对构建基于智能图像识别的产品检测系统具有一定的工业参考价值。     

基于机器视觉的玻璃缺陷检测

随着科学技术的进步,高端显示屏产品对平板玻璃的质量要求越来越高,玻璃的表面缺陷检测技术也因此备受关注。传统的人眼检测方法工作量大且准确率低,已经无法满足生产实际要求。研究了一种基于机器视觉的玻璃质量检测系统,采用先进的CCD成像技术和背光式照明获取图像,用MATLAB图像处理工具箱对采集到的图像进行灰度值化、滤波降噪和阈值分割处理,实现对缺陷区域的特征提取和识别。最后用BP神经网络对玻璃表面的三种缺陷进行分类,该神经网络识别的平均误差率为9.84%,表明此检测方法具有一定的应用价值。     

无缝钢管斜轧穿孔顶头表面缺陷非接触在线检测方法

针对无缝钢管斜轧穿孔顶头表面缺陷在线检测的现实需求，提出了一种基于激光扫描、空间点云数据处理及深度学习的非接触测量方法。根据无缝钢管产线特点确定了检测位置、系统构成和顶头轮廓数据采集方案，并引入迭代最近点（ICP）配准方法，实现了测量点云与标准CAD模型的配准。针对头部缺陷设计了相应的分类数集和渐变形态，使用点云深度学习方法实现了缺陷精确分类和量化预警。针对表面磨损缺陷，设置磨损深度上限阈值以实现磨损程度的精确监测。为验证系统可靠性，搭建了顶头检测物理模拟平台，并利用3D打印技术定制了含有不同缺陷特征的顶头实物模型。测试结果表明，表面轮廓检测误差在0.06 mm以内，头部缺陷分类精度可达97.7%、准确度可达98.1%，满足在线检测要求。     

AUTOMATIC INSPECTION SYSTEM FOR DEFECTS OF PRINTED ART TILE BASED ON TEXTURE FEATURE ANALYSIS

An automatic inspection system of printed art tile defects is reported in this artucke. After calculating eight defect features of art tile using the gray level co-occurrence matrix and the average R, G, B values of a defective area, the results were input into a backward propagation neural network for training the defect classifier. During inspection, the proposed system compared the inspected image with a standard image and removed noise by an erosion operation in order to preliminarily determine whether the art tile had defects. For the defective art tile images, the proposed classifier successfully identified four types of common printing defects. The proposed algorithm had an average recognition rate of 90%, suggesting that the recognition accuracy is good, and only requires 1–2 s to inspect an art tile with the size of 15 × 15 cm². The inspection speed is faster than the conventional manual inspection, and recognition results are more stable. The proposed system can reduce the risk of error caused by the long duration of manual inspection, and thus, can reduce manufacturing costs.     

Online monitoring and measurements of tool wear for precision turning of stainless steel parts

Online monitoring and measurements of tool wear were carried out using cutting forces for precision turning of stainless steel parts. The best combination of features was selected from 14 features extracted from force signals by using a Sequential Forward Search algorithm. Back-propagation neural networks (BPNs) used two features for online classification. When the adaptive neuro-fuzzy inference system (ANFIS) was applied, seven features were needed for the classification. For online measurements, only one feature is needed for BPN. Three features are needed for ANFIS for online measurements. For online classification of turning tool conditions, a 2?×?20?×?1 BPN can achieve a success rate of higher than 86% while a 7?×?2 ANFIS can reach a success rate of higher than 96%. For online measurements of tool wear, the estimation error can be as low as 1.37% when a 1?×?20?×?1 BPN was used while the error can be as low as 0.56% using a 3?×?3 ANFIS. Therefore, the 3?×?3 ANFIS can be used first to predict the degradation of tool conditions during the turning process. It can also be used to measure the tool wear online so as to take feedback control action to enhance accuracy of the process. Once the detected tool wear is close to the worn-out threshold, the 7?×?2 ANFIS will be then applied to classify the tool conditions in order to stop the turning operation on time automatically so as to assure the quality of products and to avoid catastrophic failure.     

超声锁相热像技术检测接触界面类型缺陷

为了提高超声锁相热像技术(ULT)的检测效率并获得最佳检测结果,对超声波调制、热图序列处理和检测参数选择进行了研究。阐述了超声锁相热像技术的检测原理并进行了理论分析,建立了ULT的检测系统。采用方波调制的超声波激励试件,用红外热像仪记录试件表面热图,并用瞬态处理方法对热图进行锁相处理得到相位图和幅值图实现对缺陷的检测。用该方法检测了钢板表面及近表面的微裂纹(微米级)和铝合金板内不同深度缺陷等接触界面类型缺陷。结果表明,检测A3钢板材料表面(近表面)裂纹时,调制频率可选择0.5Hz,接触压力约0.25kN,激励头与微裂纹的距离对检测结果几乎无影响,激励位置可根据试件结构而确定;由于降低调制频率可提高缺陷的检测深度,检测铝合金材料时,调制频率≤0.3Hz能够探测到4mm深度的缺陷;另外,该方法能够准确检测蜂窝夹层结构的脱粘缺陷。研究表明,研制的检测系统数秒内即可完成对接触界面类型缺陷的准确检测。     

轴承套圈端面缺陷在线视觉检测的研究与实现

针对轴承生产企业套圈生产过程中普遍存在端面缺陷的问题与人工目检的现状,提出了基于机器视觉的轴承套圈端面缺陷在线检测方法.首先,对套圈图像预处理后进行边缘检测,采用四连通域定位套圈端面区域;其次,采用最小二乘法拟合端面轮廓以判别外形缺陷,采用极坐标变换将套圈环形端面拉伸成矩形,采用Sauvola局部二值化算法对矩形图进行...     

Industrial x-ray inspection system with improved image characterization using blind deblurring based on compressed-sensing scheme

An industrial x-ray inspection system has recently established by our group to examine large and dense objects available in industry. It consists of an industrial x-ray generator having a tube voltage of 450?kV and a focal spot size of 1?mm, a flat-panel detector having a pixel size of 200?µm and a pixel dimension of 2048?×?2048, and a mechanical support for object’s installation. For improving the image characteristics of the system, an effective blind deblurring method based on compressed-sensing scheme is reported. Blind deblurring is the image restoration by estimating the original image and the degradation mechanism using partial information on both. Compressed-sensing is a relatively new mathematical theory for solving the inverse problems. Systematic measurements were performed and the image characteristics of the restored images were quantitatively evaluated using several image-quality indicators. The results demonstrate that the deblurring method is effective for industrial x-ray inspection systems.     

钢板表面微裂纹的超声锁相热像检测技术研究

为了提高超声锁相热像技术(ULT)的检测效率并获得最佳检测结果,对超声波调制、热图序列处理和检测参数选择进行了研究。阐述了超声锁相热像技术的检测原理,进行了理论分析;建立了ULT的检测系统,采用幅值方波调制的超声波对试件进行激励,利用红外热像仪记录热图,通过锁相处理得到试件表面热波的相位图和幅值图,利用幅值图和相位图实现钢板表面微裂纹的检测。结果表明：对于A3钢板材料,调制频率选择0.5Hz,接触压力仅需保证激励试件时激励头与试件接触不脱离,约0.25kN,激励头与表面微裂纹的距离对检测结果几乎无影响,激励位置可根据试件结构而确定。研制的超声激励装置组成的检测系统可数秒内即可完成对钢板表面微裂纹（微米级）的准确检测。     

基于条纹反射的陶瓷球表面缺陷快速检测算法

陶瓷球是一种广泛应用于精密轴承的基础零件,目前尚无成熟的陶瓷球表面缺陷检测设备。为此设计了一种基于条纹反射的陶瓷球表面缺陷快速视觉检测算法。该算法借助图像预处理、灰度累积差分定位、边缘检测、行间差分及模板匹配等方法来定位特征点,然后根据其数量评判球面是否存在缺陷。对直径6.35 mm的黑色氮化硅陶瓷球进行了检测,单幅灰度图缺陷检测时间0.78秒,检测极限为16.5μm。     

An automatic optical inspection of drill point defects for micro-drilling

This study develops an automated visual inspection system for detecting and classifying defects in a micro-drill with 0.35 mm diameter using image processing techniques. The orientation of the micro-drill is first determined through image projection. Next, the digital image captured by the CCD is then segmented into regions of interest (ROI). The randomized line detection algorithm and the geometric relationship of the edge points in the ROI are then employed to identify the defects detected. Experimental results show that the developed automatic visual inspection system is as efficient as manual inspection, and can provide additional information concerning the defects for parameters tuning and quality control.     

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。     

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.     

基于图像处理器的圆锥滚子表面缺陷在线检测系统

研制了一种圆锥滚子表面缺陷在线检测系统。该系统由机械装置和控制系统等组成,机械装置自动完成被测工件的上料、定位、检测、剔除及下料;控制系统由PLC完成工作过程控制,由图像处理器完成缺陷检测的图像处理与判定结果输出。实验结果表明,系统可检测最小直径0.1m(与相机分辨率有关)的表面缺陷,速度为2s/个。该系统检测精度高、测量数度较快,实现了无人在线检测,满足滚子表面缺陷的检测要求。     

等离子高分子导电薄膜的微型机器鱼图像分析

ICPF是能够被1.5 V低电压驱动的等离子高分子导电薄膜,具有质量轻、响应速度快的特点。用长21.6 mm、宽4.6 mm、厚0.2 mm的ICPF薄膜驱动的微型机器人能够以3 mm/s的速度在水中运动。为了对其运动姿态进行检测和控制,设计了微型机器人的图像处理系统,此系统由CCD摄像机、图像接口卡、计算机和波形发生器组成。通过CCD摄像机获取机器人的运动图像序列;利用目标短时相似性,对每一帧图像进行色调自动阈值分割和边缘提取得到目标二值图像;采用改进的Hough圆变换计算出目标在图像中的位置和运动方向。最后,根据目标的位置和运动方向,通过波形发生器,改变ICPF两端的电压和频率来实现对机器鱼姿态的控制。本系统在Pentium 4 2.8 G内存1 G的电脑上,处理一张图片需52 ms,可以实现对机器人的实时检测、跟踪和控制。     

基于数字图像处理的印刷电路板缺陷检测

针对传统PCB检测方法高成本、低效率问题,提出一种基于数字图像处理的PCB板自动光学检测方法,建立了将标准图像和待测图像进行对比的检测系统。针对PCB板生产过程中遇到的短路、断路、空洞、凸起、凹陷等缺陷,采用了求连通区域数、计算欧拉数、求缺陷区域面积等方法,来检测上述缺陷问题,并给出算法的全过程。经实验结果分析,该方法能准确地检测出待检测电路板上存在的缺陷,达到了自动实时检测的目的。     

宽幅胶片弊病在线检测系统

本文介绍了一套用于宽幅胶片生产线整理工序的弊病在线检测系统，该系统用来实时检测胶片表面常见的弊病。系统采用2台线阵CCD摄像机同步成像，940nm的LED面阵光源提供照明，利用单行处理、多行判断的快速弊病检测算法及时发现弊病。现场运行结果表明，系统能够完成对运行速度为90m／min，宽幅为1300mm的胶片表面弊病的检测任务。     

电缆连接器滑轨自动化光学检测设备开发

针对传统电缆连接器的品质控管中人眼目视判定存在人为误判的缺点,开发整合尺寸测量与瑕疵检测为一体的自动化检测机台。利用NI运动控制模组将待测物移动至光学取像模组正下方,通过CCD获取工件表面状态影像,利用傅里叶变换与小波变换算法对影像进行分析比较,实现牙孔特征检测;利用二值化与膨胀算法实现断差检测;利用二值化与腐蚀算法实现柱脚检测,从而判定该待测物是否符合设计规范。实验结果表明,该自动化光学检测设备能够正确辨识良品与不良品,满足厂商对品质控管的需求。