一种基于深度学习的软管空管异物检测方法  

A Method for Detecting Foreign Matter in Empty Hoses Based on Deep Learning

作　　者：孙克强 张义伟[1] 沈宝诚[1] SUN Keqiang;ZHANG Yiwei;SHEN Baocheng(The 41st Research Institute of CETC,Bengbu 233010,China)

机构地区：[1]中国电子科技集团公司第四十一研究所,安徽蚌埠233010

出　　处：《安徽电子信息职业技术学院学报》2023年第4期6-9,14,共5页Journal of Anhui Vocational College of Electronics & Information Technology

摘　　要：文章介绍了使用计算机视觉技术获取软管空管图像,采用一种基于深度学习的异物检测算法对软管空管进行质量检测,检测软管空管在灌装前是否存在异物的质量缺陷,从而确保软管空管的产品质量。该方法有效地降低了工业产品的误检率和漏检率,具有良好的泛化能力,已成功用于生产实际,能够准确地用于软管空管异物检测,具有一定的推广价值。The paper introduces how to use the detection algorithm to detect the quality of empty hose pipes after using computer vision technology to obtain images of empty hose pipes.Detect whether there are quality defects before the empty tube of the hose is filled,so as to ensure the product quality of the empty tube of the hose.The proposed method effectively reduces the rates of false detection and missing detection in industrial products,demonstrating excellent generalization capabilities.It has been successfully applied in practical production and can be accurately utilized for detecting foreign bodies in empty pipes,thus possessing a certain promotion value.

关 键 词：计算机视觉 软管空管 分类检测 灌装 质量缺陷 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]