基于网格分割的多尺度酒瓶缺陷检测研究

吴仕莲1,胡 涛2,汪增福1,郑志刚1,赵丙坤2*,祝燕林2,杨 洋2

1.中国科学技术大学信息科学技术学院,安徽合肥 230000

2.泸州老窖股份有限公司,四川泸州 646000

摘要:近年来,深度学习技术在不同计算机视觉任务中都取得了重大突破,基于深度学习的视觉检测方法具有精度高、鲁棒性强的优势。本文针对酒瓶包装缺陷检测领域进行研究,设计了一种基于网格的多尺度缺陷检测模型,通过对原始图像划分网格,将缺陷映射到对应网格位置以解决缺陷形状多样、难以定义的问题;并在不同尺度的特征上检测缺陷,解决酒瓶缺陷尺度变化大的问题。

关键词:缺陷检测;深度学习;多尺度;全卷积网络

中图分类号:TS206.1   文献标识码:A   文章编号:1674-506X202305-0104-0005


Multi-scale Bottle Defect Detection Based on Grid Segmentation

WU Shilian1HU Tao1WANG Zengfu1ZHEN Zhigang1ZHAO Bingkun2*ZHU Yanlin2YANG Yang2

1.School of Information Science and Technology, University of Science and Technology of China,

Hefei Anhui 230000, China;

2.Luzhou Laojiao Co., Ltd., Luzhou Sichuan 646000, China

AbstractIn recent years, deep learning technologies have made significant breakthroughs in various computer vision tasks. Deep learning- based visual inspection methods offer advantages such as high accuracy and strong robustness. This paper focuses on the field of bottle defect detection and presents a research study that designs a multi-scale defect detection model based on grids. By dividing the original image into grids, defects are mapped to their respective grid positions to address the issue of diverse and hard-to-define defect shapes. Additionally, defects are detected on features at different scales, addressing the challenge of varying defect scales in glass bottle defects.

Keywordsdefect detection; deep learning; multi-scale; fully convolutional network

doi10.3969/j.issn.1674-506X.2023.05-018


收稿日期:2023-30-12

作者简介:吴仕莲(1994-)男,博士,工程师。研究方向:缺陷检测。

*通信作者:赵丙坤(1979-)男,本科,高级工程师。研究方向:包材采购、包装设备开发。


引用格式:吴仕莲,胡涛,汪增福,.基于网格分割的多尺度酒瓶缺陷检测研究[J].食品与发酵科技,2023,59(5):104-108.


全文查看

公告通知

联系我们

  • 双月刊

  • 四川省经济和信息化厅

  • 四川省食品发酵工业研究设计院有限公司

  • 《食品与发酵科技》编辑部

  • 四川省成都市温江区杨柳东路中段98号

  • 611130

  • 028-82763572

  • ISSN1674-506X

  • CN51-1713/TS

  • 62-247