基于神经网络的零件缺陷机器视觉识别系统  

Computer Vision Recognition System for Component Defect Based on Neural Network

作　　者：李鹤[1] 

机构地区：[1]沈阳工学院,辽宁抚顺113122

出　　处：《计算机测量与控制》2017年第11期248-251,256,共5页Computer Measurement &Control

摘　　要：小轴承、轮轴等是机器、车辆、发动机等的重要零配件,为提高对其表面缺陷进行检测的检测效率和检测精度,以小轴承表面为研究对象,提出了采用机器视觉技术实现对轴承表面缺陷的实时在线自动检测,设计了基于BP神经网络的零件缺陷机器视觉在线自动检测系统;根据微小轴承的表面结构、尺寸、检测精度和缺陷特征,采用机器视觉技术,对所采集到的图片进行预处理,构建BP神经网络检测识别模型,利用Hough变换以及Roberts算子提取了图像中的目标区域,以组合矩不变量为依据,判断轴承是否存在缺陷,从而对微小轴承缺陷进行实时检测;MATLAB仿真结果证明了人工神经网络识别模型的检测能力的可靠性和有效性。Small bearings, axles, and ete are important components for machines, vehicles, engines and etc. In order to improve the de- tection efficiency and detection accuracy of its surface defects, Taking small hearing surface as the ohiect of study, and putting forward the method to realize real--time online automatic detection of hearing surface defects based on machine vision technology and designing the online automatic detection system of defective parts machine vision based on BP neural network. According to the micro bearings surface structure, size, accuracy and deject characteristics, using machine vision technology, preprocessing for the collected image, and constructing BP neural network detective model, extracting target area in the image by Hough transform and Roberts operator. Based on the combined-- moment in- variants, the defects of the bearings are judged, and thus the defects of the small bearings are detected in real time. The simulation results of MATLAB verify the reliability and effectiveness of ANN detection model.

关 键 词：缺陷检测 神经网络 机器视觉 组合矩 

分 类 号：E926.3[军事—军事装备学]