Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (10): 2899-2903.DOI: 10.11772/j.issn.1001-9081.2020020143

• Artificial intelligence • Previous Articles     Next Articles

Ampoule packaging quality inspection algorithm based on machine vision and lightweight neural network

GAO Ming, REN Dejun, HU Yunqi, FU Lei, QIU Lyu   

  1. School of Mechanical Engineering, Sichuan University, Chengdu Sichuan 610065, China
  • Received:2020-02-15 Revised:2020-03-31 Online:2020-10-10 Published:2020-04-13


郜明, 任德均, 胡云起, 付磊, 邱吕   

  1. 四川大学 机械工程学院, 成都 610065
  • 通讯作者: 任德均
  • 作者简介:郜明(1996-),男,安徽阜阳人,硕士研究生,主要研究方向:机器视觉、机器学习;任德均(1972-),男,四川南充人,副教授,博士,主要研究方向:机器智能、机器视觉;胡云起(1995-),男,江西赣州人,硕士研究生,主要研究方向:智能控制、机器视觉;付磊(1995-),男,江西丰城人,硕士研究生,主要研究方向:深度学习、图像处理;邱吕(1996-),女,四川广安人,硕士研究生,主要研究方向:图像处理、机器学习。

Abstract: Focusing on the problems such as low inspection speed and low accuracy caused by subjective factors in the manual inspection method of ampoule packaging quality, an inspection algorithm based on machine vision and lightweight neural network was proposed. First, threshold processing, tilt correction and cutting of ampoule regions were performed on the images to be inspected by using the threshold segmentation and affine transformation methods in machine learning. Second, the network structure of the classification algorithm was designed according to the characteristics of images and the requirements of defect recognition. Finally, the ampoule packaging defect dataset was constructed by collecting the images of the production site. After that, the proposed ampoule packaging defect identification network was verified, and the accuracy and inspection speed of the algorithm deployed on the Jetson Nano embedded platform were tested. Experimental results show that, taking the product of five ampoules each box as the example, the proposed ampoule packaging quality inspection algorithm takes 70.1 ms/box averagely, that is up to 14 boxes/s, and has the accuracy of 99.94%. It can achieve online high-precision ampoule packaging quality inspection on the Jetson Nano embedded platform.

Key words: machine vision, ampoule packaging, Convolutional Neural Network (CNN), quality inspection, Jetson Nano embedded platform

摘要: 针对人工检测安瓿瓶包装质量时存在的速度慢以及受主观因素影响导致的准确率低等问题,提出一种机器视觉和轻量级卷积神经网络结合的安瓿瓶包装质量检测方法。首先,采用机器视觉中基于阈值分割以及仿射变换的方法对待测图片进行阈值处理、倾斜校正和安瓿瓶区域的裁剪;然后,根据图像特点以及缺陷识别要求设计分类算法的网络结构;最后,采集生产现场图片构建安瓿瓶包装缺陷数据集,之后对提出的安瓿瓶包装缺陷识别网络进行了验证,并测试了部署在Jetson Nano嵌入式平台上的算法的准确率及检测速度。实验结果表明:以每盒五支装的产品为例,所提安瓿瓶包装质量检测算法平均每盒耗时70.1 ms,即可达14盒/秒,而准确率为99.94%,能够实现在Jetson Nano嵌入式平台上的在线高精度安瓿瓶包装质量检测。

关键词: 机器视觉, 安瓿瓶包装, 卷积神经网络, 质量检测, Jetson Nano嵌入式平台

CLC Number: