《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (5): 1440-1446.DOI: 10.11772/j.issn.1001-9081.2021050834

• 人工智能 • 上一篇    下一篇

基于深度特征融合的无纺布低对比度浆丝缺陷检测方法

鲁永帅, 唐英杰(), 马鑫然   

  1. 北京印刷学院 信息工程学院,北京 102600
  • 收稿日期:2021-05-18 修回日期:2021-09-09 接受日期:2021-09-16 发布日期:2021-09-09 出版日期:2022-05-10
  • 通讯作者: 唐英杰
  • 作者简介:鲁永帅(1996—),男,河南项城人,硕士研究生,主要研究方向:深度学习、图像处理
    唐英杰(1963—),男,安徽砀山人,副教授,硕士,主要研究方向:机器视觉、图像处理 tangyj@bigc.edu.cn
    马鑫然(1996—),女,北京人,硕士研究生,主要研究方向:深度学习、图像处理。
  • 基金资助:
    北京市自然科学基金项目-北京市教委科技计划重点项目(KZ202010015021)

Low contrast filament sizing defect detection method of non-woven fabric based on deep feature fusion

Yongshuai LU, Yingjie TANG(), Xinran MA   

  1. College of Information Engineering,Beijing Institute of Graphic Communication,Beijing 102600,China
  • Received:2021-05-18 Revised:2021-09-09 Accepted:2021-09-16 Online:2021-09-09 Published:2022-05-10
  • Contact: Yingjie TANG
  • About author:LU Yongshuai, born in 1996,M. S. candidate. His researchinterests include deep learning,image processing.
    TANG Yingjie,born in 1963,M. S.,associate professor. Hisresearch interests include machine vision,image processing.
    MA Xinran, born in 1996,M. S. candidate. Her research interestsinclude deep learning,image processing.
  • Supported by:
    Beijing Natural Science Foundation Project-Beijing Municipal Education Commission Science and Technology Plan Key Project(KZ202010015021)

摘要:

针对无纺布生产过程中产生的浆丝缺陷对比度较低,以及传统图像处理方法对其检测效果较差的问题,提出了一种基于卷积神经网络(CNN)的无纺布低对比度浆丝缺陷检测方法。首先,对采集到的无纺布图像进行预处理以构建浆丝缺陷数据集;然后,利用改进的卷积神经网络以及多尺度特征采样融合模块构造编码器以提取低对比度浆丝缺陷的语义信息,并在解码器中采用跳跃连接进行多尺度特征融合来优化上采样模块;最后,通过所构建的数据集训练网络模型,从而实现低对比度浆丝缺陷的检测。实验结果表明,所提方法可以有效定位并检测出无纺布上的低对比度浆丝缺陷,其平均交并比(MIoU)、类别平均像素准确率(MPA)分别可以达到77.32%和86.17%,单张样本平均检测时间为50 ms,能够满足工业生产的要求。

关键词: 无纺布, 低对比度, 浆丝缺陷, 语义分割, 深度学习

Abstract:

In order to solve the problem of poor detection effect of traditional image processing methods for the low contrast filament sizing defects in non-woven fabric production process, a low contrast filament sizing defect detection method of non-woven fabric based on Convolutional Neural Network (CNN) was proposed. Firstly, the collected non-woven fabric images were preprocessed to construct a defect dataset of filament sizing. Then, an improved convolutional neural network and a multi-scale feature sampling fusion module were used to construct an encoder to extract the semantic information of low contrast filament sizing defects, and a skip connection was used in the decoder to achieve multi-scale feature fusion for optimizing the upsampling module. Finally, the low contrast defect detection of filament sizing was realized by training the network model on the constructed dataset. Experimental results show that, the proposed method can effectively locate and detect the low contrast filament sizing defects on non-woven fabric. The Mean Intersection over Union (MIoU) and category Mean Pixel Accuracy (MPA) of the proposed method can reach 77.32% and 86.17% respectively, and the average detection time of single sample of the proposed method is 50 ms, which can meet the requirements of industrial production.

Key words: non-woven fabric, low contrast, filament sizing defect, semantic segmentation, deep learning

中图分类号: