计算机与现代化

• 算法设计与分析 • 上一篇    下一篇

基于ResNet网络的医用塑瓶制造缺陷检测方法

  

  1. (四川大学机械工程学院,四川成都610065)
  • 收稿日期:2019-08-14 出版日期:2020-04-22 发布日期:2020-04-24
  • 作者简介:付磊(1995-),男,江西丰城人,硕士研究生,研究方向:机器视觉,E-mail: fuleijx2018@163.com; 通信作者:任德均(1971-),男,四川成都人,副教授,硕士生导师,博士,研究方向:嵌入式系统,机电一体化,机器视觉,E-mail: rendejun@scu.edu.cn; 胡云起(1995-),男,硕士研究生,研究方向:机器视觉,E-mail: 1119063534@qq.com; 郜明(1996-),男,硕士研究生,研究方向:机器视觉,E-mail: 1204563110@qq.com; 邱吕(1996-),女,硕士研究生,研究方向:机器视觉,E-mail: 2391361235@qq.com。

Defect Detection Method for Medical Plastic Bottle Manufacturing Based on ResNet Network

  1. (School of Mechanical Engineering, Sichuan University, Chengdu 610065, China)
  • Received:2019-08-14 Online:2020-04-22 Published:2020-04-24

摘要: 本文提出一种基于深度学习的识别方法用于医用塑瓶气泡、积料等生产缺陷的实时检测,设计工业现场的视觉检测硬件平台,细述积料与气泡检测算法的原理,简述算法检测前的图像预处理。在Pytorch框架下通过ResNet系列算法与MobilenetV2算法的正交实验对积料检测实时性能进行比较,同时优化RetinaNet网络在气泡上的检测性能。在生产现场中该方法关于积料的平均检测精度为99.7%,单幅图片检测时间为29.7 ms;气泡的Fβ指数为99.5%,单幅图片检测时间为35.5 ms,达到企业生产的要求。

关键词: 医用塑瓶, 图像处理, 深度学习, 目标检测

Abstract: This paper proposes a recognition method based on deep learning for the real-time detection of production defects such as medical plastic bottle bubbles and accumulated materials, designs the visual inspection hardware platform of the industrial site, describes the principle of the accumulation and bubble detection algorithm, and briefly describes the image pre-processing before the algorithm detection. Under the Pytorch framework, the real-time performance of aggregate detection is compared by orthogonal experiment between ResNet series algorithms and MobilenetV2 algorithm, and the detection performance of RetinaNet network on the bubbles is optimized.At the production site, the average detection accuracy of the proposed method is 99.7% and the single detection time is 29.7 ms. The Fβ index of the bubble is 99.5% and the single detection time is 35.5 ms, which meets the requirements of enterprise production.

Key words: medical plastic bottle, image processing, deep learning, target detection

中图分类号: