基于机器视觉的玻璃表面缺陷检测系统的研究

介绍了玻璃表面缺陷检测方法与原理,研究开发了基于机器视觉的玻璃表面检测系统.针对实际的目标图像,通过对其进行图像获取、图像预处理、图像分割、特征提取和区域参数计算研究, 从而获得玻璃表面缺陷图像的识别信息.实验表明,该算法简单、速度快、系统抗干扰能力强,能满足实际使用的要求.     

浮法玻璃缺陷在线检测识别方法研究

提出了一种基于机器视觉的分布式浮法玻璃缺陷在线检测识别方法。针对采集到玻璃图像为非均匀图像的特点,首先对图像进行平滑滤波处理,剔除信号波动带来的灰度尖峰和毛刺,然后设计了基于自跟踪的向下阈值曲面分割方法实现缺陷和背景的分割,实现了基于扫描线的图像搜索算法保证缺陷寻找的速度,并利用神经网络对缺陷进行分类。实际应用表明,该系统能够准确可靠的实现在线检测和识别浮法玻璃缺陷,满足了浮法玻璃企业对玻璃缺陷实时检测的需要。     

浮法玻璃质量在线检测与分析系统

介绍了一种基于机器视觉的浮法玻璃质量在线检测系统。该系统利用分布式机器视觉处理技术、采用模块化的图像处理方法,实现了缺陷的精确检测和提取,能够对缺陷进行智能分类和分级,并根据缺陷数据对玻璃进行分级打标,满足了浮法玻璃生产中缺陷在线检测的需要。     

基于莫尔条纹的玻璃缺陷检测技术研究

玻璃缺陷直接影响玻璃的质量,因而玻璃缺陷的检测成了提高玻璃质量的重要技术保障之一.在浮法玻璃生产线必须进行质量检测,对不符合格的玻璃进行切除.为有效的对玻璃缺陷进行检测,本文提出一种基于莫尔条纹的玻璃缺陷检测方法,该方法不但能够有效检测出玻璃的缺陷,同时还能根据缺陷的性质将其分类.     

基于线阵CCD的玻璃缺陷检测方法的研究

玻璃缺陷检测已成为提高玻璃质量的重要技术之一，它在检测出不合格玻璃产品的同时，还能将缺陷信息传递给玻璃生产的各个流程，再对各个环节加以改进。为能够生产出高质量的玻璃，以及准确获取玻璃缺陷信息，本文提出了一种基于莫尔条纹的玻璃缺陷检测新方法。这种检测方法不但能够检测出微小缺陷，并进行分类，同时还能有效地检测出玻璃的光学畸变。     

浅析光源在玻璃基板检测中的应用

玻璃基板是显示器屏幕无法替代的材料,其缺陷检测显得尤为重要。文章就不同光源对基板玻璃缺陷的检测进行了论述,以期对生产和加工行业的玻璃基板缺陷检测有指导意义。     

玻璃缺陷在线检测系统常见问题的解决方法

玻璃缺陷在线检测系统在玻璃生产行业获得广泛应用,通过智能相机,其能够不间断地对玻璃带进行检测。系统检测出来的缺陷类型、尺寸大小及缺陷位置等重要数据发送到线控,再由线控进行优化切割,可以在很大程度上提高生产效率。在生产过程中有时会有缺陷漏检、核心尺寸不稳定等情况出现。根据在调试过程中遇到的一些问题,提出了如何能够快速找到问题产生原因和解决问题的方法。     

液晶玻璃基板边检问题分析与对策

玻璃基板成形清洗后需要利用仪器检测缺陷,一般采用机器视觉的方法检测玻璃缺陷。目前,在生产流程中发现检查机边检显示界面边部缺失。本文主要通过对边检检查机进行原理分析,推断为传感器位置发生偏移以及玻璃不到位等因素导致问题的产生,因此对传感器位置、玻璃传送速率以及相关设置参数进行调整,提出相关对策解决边部缺失问题。生产线反馈及监测,效果良好。     

基于变异系数法的工业产品表面缺陷快速检测应用研究

为了提高工业产品质量控制中表面缺陷检测的准确性和快速性,提出了一种基于机器视觉的工业产品表面缺陷快速检测方法。方法引用变异系数的概念,通过待检测图像和模板图像进行差运算得到差影图像,并通过计算其变异系数以确定阈值,利用分割定位缺陷,从而实现缺陷的快速检测。壁纸表面缺陷检测实验结果表明,本方法提高了图像检测系统的准确性和鲁棒性,误检率大大降低。     

机器视觉技术在玻璃基板缺陷检测设备中的应用

简单介绍了机器视觉的基本概念及相关组成,分析了以机器视觉为理论基础的光学检测设备在玻璃基板缺陷检测中的应用。通过对玻璃基板常见缺陷的介绍,指出了相关检测设备在具体的缺陷检测中需要注意的事项。     

玻璃缺陷在线检测技术研究

讨论了玻璃缺陷的几种常见类型,探讨了基于计算机视觉、图像处理技术的自动化解决方案。     

Automatic fabric defect detection using a deep convolutional neural network

Fabric defect detection plays an important role in the textile production process, but there are still some challenges in detecting defects rapidly and accurately. In this paper, we propose a powerful detection method for automatic fabric defect detection using a deep convolutional neural network (CNN). It consists of three main steps. First, the fabric image is decomposed into local patches and each local patch is labelled. Then the labelled patches are transmitted to the pretrained deep CNN for transfer learning. Finally, defects are detected during the inspection phase by sliding over the whole image using the trained model, and the category and position of each defect is obtained. The proposed method is validated on two public and one self‐made fabric database. The experimental results demonstrate that our method significantly outperforms selected state‐of‐the art methods in terms of both quality and robustness.     

Research and Development of Intelligent On-Line Real-time Defect Inspection System for Polymer Polarizer

This paper aimed at developing a set of on-line real-time defect inspection system for Polymer polarizer. It intended to help producers make different improvements for the spot or line defects in manufacturing on-line polarizer. This paper used line-scan charged couple device (CCD) to capture the defect images of polarizer: firstly, to scale down the captured images by 64 times with downsampling compression; then, we utilized Laplace operator to find out the edges of defects and the shield with isotropic results for 45° and 90° incremental rotation. Subsequently, we used the statistical decision method of threshold value to divide up the edges of defects that were discovered with Laplace operator from the image. Eventually, we differentiated the spot defects, like dust, foreign objects, scars of hit and air bubbles in the production process from the line defects, like scratches in the follow-up handling process with the straight line detection characteristic of Hough Transform. This paper captured 200 pieces of defect images of polarizer samples in all and then input them to the inspection system developed by ourselves for test. The differentiation rate of defects amounted to 98%, which proved that we had successfully developed a set of on-line real time automatic optical inspection (AOI) system suitable to be applied to polymer polarizer.     

In-TFT-Array-Process Micro Defect Inspection Using Nonlinear Principal Component Analysis

Defect inspection plays a critical role in thin film transistor liquid crystal display (TFT-LCD) manufacture, and has received much attention in the field of automatic optical inspection (AOI). Previously, most focus was put on the problems of macro-scale Mura-defect detection in cell process, but it has recently been found that the defects which substantially influence the yield rate of LCD panels are actually those in the TFT array process, which is the first process in TFT-LCD manufacturing. Defect inspection in TFT array process is therefore considered a difficult task. This paper presents a novel inspection scheme based on kernel principal component analysis (KPCA) algorithm, which is a nonlinear version of the well-known PCA algorithm. The inspection scheme can not only detect the defects from the images captured from the surface of LCD panels, but also recognize the types of the detected defects automatically. Results, based on real images provided by a LCD manufacturer in Taiwan, indicate that the KPCA-based defect inspection scheme is able to achieve a defect detection rate of over 99% and a high defect classification rate of over 96% when the imbalanced support vector machine (ISVM) with 2-norm soft margin is employed as the classifier. More importantly, the inspection time is less than 1 s per input image.     

磁致伸缩导波技术在工业管道腐蚀检测中的应用

介绍了磁致伸缩导波检测管道腐蚀缺陷的原理,并采用MsSR3030R导波检测系统对钢质常温压缩空气管道和高温水蒸汽管道(工作温度198℃)进行了现场在线检测。结果表明,该技术可以发现管道发生的腐蚀缺陷,并较为准确地确定其长度方向上的位置,但不能确定缺陷的性质,需要通过其他检测手段进行确认。同时,该技术现场检测的有效长度受到焊缝、支架、弯管等因素的影响较大。     

针织用涤纶短纤维的疵点检测

针织用涤纶短纤维对纤维质量特别是疵点的含量要求较高,目前纤维中疵点的检验方法有手检法和原棉分析机法,这两种方法只能检出质量在0.1 mg以上的疵点,而针织用短纤更关注0.1 mg以下的小疵点,现有的分析方法无法满足下游纺织用户的质量要求。建立了一种新的疵点检验方法——染色疵点分析方法,先对纤维进行染色,然后再挑出异常纤维即疵点。     

基于机器视觉的塑料制品外观缺陷检测

为了克服传统人工检测方法效率低、自动化和智能化程度低等缺陷,设计了一种基于机器视觉的塑料制品外观缺陷检测方法,利用摄像机进行制品外观缺陷检测,实现制品生产流水线的自动化、智能化检测.介绍了机器视觉检测系统组成.为了提高机器视觉检测系统准确率,对采集到的图像进行了均值滤波和边缘分割检测.结果表明:机器视觉检测系统能够实现...     

低频导波与远场涡流组合检测技术及其应用

在对低频导波与远场涡流技术原理进行初步分析的基础上,提出了低频导波与远场涡流组合技术应用于工业管道腐蚀缺陷检测的方法:首先用低频导波技术对管道进行快速扫描,在发现异常信号区域,利用远场涡流技术进行缺陷精确定位并量化。利用该组合技术对某架空管段缺陷进行了检测应用,结果表明两种技术能相互补充,并有效提升了管体腐蚀缺陷的检测效果。