摘要
随着现代科技的发展,透明件几乎运用于各个行业并起着不可或缺的作用,透明件表面质量是衡量其合格与否的一个重要指标,同时机器视觉技术因具有速度快、精度高、成本低、稳定性好等优点被广泛用于透明件表面缺陷的检测。本文主要从图像采集、图像处理和缺陷识别几个环节来介绍透明件表面缺陷的检测,对检测系统的类型,采集图像的处理方法以及实验数据的整理进行深入的研究,结合图像特征与深度学习方法对透明件表面缺陷进行归类,探讨机器视觉检测透明件技术发展近状及现存问题。进一步,本文阐述了机器视觉检测透明件的最新进展,并对未来可能发展趋势进行预测,为后续研究工作提供基础理论参考。
The surface quality of transparent parts is an important indicator to measure whether they are qualified or not.Computer vision technology is widely used in the detection of surface defects of transparent parts because of its advantages such as high speed,high precision,low cost and good stability.This paper mainly introduces the detection of the surface defects of transparent parts with image acquisition,image processing and defect recognition.This paper uses the image feature method and the deep learning method to classify the surface defects of transparent parts and discusses the recent developments and existing problems of computer vision technology for detecting surface defects of transparent parts.
作者
明五一
贾豪杰
何文斌
魏爱云
MING Wuyi;JIA Haojie;HE Wenbin;WEI Aiyun(Zhengzhou University of Light Industry,Mechanical and Electrical Engineering,Zhengzhou 450002,China;Guangdong Provincial Key Laboratory of Manufacturing Equipment Digitization,Guangdong HUST Industrial Technology Research Institute,Dongguan 523808,Guangdong,China)
出处
《机械科学与技术》
CSCD
北大核心
2021年第1期116-124,共9页
Mechanical Science and Technology for Aerospace Engineering
基金
河南省自然科学基金项目(182300410170,182300410215)
河南省高校科技创新团队项目(182300410215)
广东省制造装备数字化重点实验室开放项目(2017B030314146)。
关键词
机器视觉
透明件
表面缺陷
检测系统
图像处理
computer vision
transparent parts
surface defect
detection system
image processing
