Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (7): 2125-2128.DOI: 10.11772/j.issn.1001-9081.2019010110

• Virtual reality and multimedia computing • Previous Articles     Next Articles

On-line fabric defect recognition algorithm based on deep learning

WANG Lishun<sup>1,2</sup>, ZHONG Yong<sup>1,2</sup>, LI Zhendong<sup>1,2</sup>, HE Yilong<sup>1,2</sup>   

  1. 1. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2019-01-17 Revised:2019-03-12 Online:2019-07-10 Published:2019-04-15
  • Supported by:

    This work is partially supported by the Sichuan Science and Technology Department Project (2018GZ0231).


王理顺1,2, 钟勇1,2, 李振东1,2, 贺宜龙1,2   

  1. 1. 中国科学院 成都计算机应用研究所, 成都 610041;
    2. 中国科学院大学, 北京 100049
  • 通讯作者: 王理顺
  • 作者简介:王理顺(1992-),男,重庆奉节人,硕士研究生,主要研究方向:大数据智能分析、机器视觉、人工智能;钟勇(1966-),男,四川岳池人,研究员,博士,主要研究方向:大数据、云计算、数据库;李振东(1990-),男,宁夏吴忠人,博士研究生,主要研究方向:机器学习、图像处理;贺宜龙(1992-),男,山东济宁人,硕士研究生,主要研究方向:数据挖掘、图像处理。
  • 基金资助:



On-line detection of fabric defects is a major problem faced by textile industry. Aiming at the problems such as high false positive rate, high false negative rate and low real-time in the existing detection of fabric defects, an on-line detection algorithm for fabric defects based on deep learning was proposed. Firstly, based on GoogLeNet network architecture, and referring to classical algorithm of other classification models, a fabric defect classification model suitable for actual production environment was constructed. Secondly, a fabric defect database was set up by using different kinds of fabric pictures marked by quality inspectors, and the database was used to train the fabric defect classification model. Finally, the images collected by high-definition camera on fabric inspection machine were segmented, and the segmented small images were sent to the trained classification model in batches to realize the classification of each small image. Thereby the defects were detected and their positions were determined. The model was validated on a fabric defect database. The experimental results show that the average test time of each small picture is 0.37 ms by this proposed model, which is 67% lower than that by GoogLeNet, 93% lower than that by ResNet-50, and the accuracy of the proposed model is 99.99% on test set, which shows that its accuracy and real-time performance meet actual industrial demands.

Key words: image processing, deep learning, convolutional neural network, defect detection


织物缺陷在线检测是纺织行业面临的重大难题,针对当前织物缺陷检测中存在的误检率高、漏检率高、实时性不强等问题,提出了一种基于深度学习的织物缺陷在线检测算法。首先基于GoogLeNet网络架构,并参考其他分类模型的经典算法,搭建出适用于实际生产环境的织物缺陷分类模型;其次利用质检人员标注的不同种类织物图片组建织物缺陷数据库,并用该数据库对织物缺陷分类模型进行训练;最后对高清相机在织物验布机上采集的图片进行分割,并将分割后的小图以批量的方式传入训练好的分类模型,实现对每张小图的分类,以此来检测缺陷并确定其位置。对该模型在织物缺陷数据库上进行了验证。实验结果表明:织物缺陷分类模型平均每张小图的测试时间为0.37 ms,平均测试时间比GoogLeNet减少了67%,比ResNet-50减少了93%;同时模型在测试集上的正确率达到99.99%。说明其准确率与实时性均满足实际工业需求。

关键词: 图像处理, 深度学习, 卷积神经网络, 缺陷检测

CLC Number: