基于Faster RCNN的布匹瑕疵识别系统
作者:
基金项目:

广州市科技计划重点领域研发计划(202007030005); 国家自然科学基金面上项目(61876067); 广东省自然科学基金面上项目(2019A1515011375)


Fabric Defect Recognition System Based on Faster RCNN
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [11]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    纺织工业是我国的支柱型产业. 在布匹生产过程中, 布匹瑕疵是影响布匹质量的关键因素. 目前纺织服装生产企业主要通过传统的人工肉眼检测布匹瑕疵, 成本高、效率低, 且漏检率与误检率高. 本研究针对布匹数据集中类别数量不均匀的特点, 对数据进行增强. 在布匹瑕疵类别识别上, 采用Faster RCNN模型, 并针对布匹数据集中瑕疵目标小的特点, 对Faster RCNN模型中的RPN网络进行改进. 另外, 本研究基于模型开发一款纺织布匹瑕疵识别系统, 将通过模型识别出的布匹瑕疵类别结果通过可视化平台展现, 同时准确标识疵点的位置. 通过实验结果对比, 本文的方法平均检测准确率为79.3%, 相比Fast RCNN提高了5.75%.

    Abstract:

    The textile industry is a pillar of China’s economy. In the supply chain of fabrics, fabric defects largely affect their quality. At present, textile production enterprises mainly rely on people’s eyes to check the quality of fabrics. This method has high cost of employment, low efficiency, and a high rate of missed and false detections, failing to meet the requirement for high-speed industrial development. This study enhances the data to address the uneven number of categories in the data set. Categories of fabric defects are identified by the Faster RCNN model, and the RPN network in the Faster RCNN model is improved regarding the small concentrated defect targets in the dataset. In addition, this study develops a fabric defect recognition system to display categories of fabric defects and precisely locate the defects. Through the comparison of experimental results, the average detection rate of this method is 79.3%, which is 5.75% higher than that of Fast RCNN.

    参考文献
    [1] 田宸玮, 王雪纯, 杨嘉能, 等. 织物瑕疵检测方法研究进展. 计算机工程与应用, 2020, 56(12): 8–18. [doi: 10.3778/j.issn.1002-8331.2002-0169
    [2] 陈健. 中国纺织工业联合会会长孙瑞哲: 科创板是纺织行业“及时雨”, 多细分领域企业有潜力. 纺织服装周刊, 2019, (11): 8. [doi: 10.3969/j.issn.1674-196X.2019.11.003
    [3] Kandaswamy U, Adjeroh DA, Schuckers S, et al. Robust color texture features under varying illumination conditions. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(1): 58–68. [doi: 10.1109/TSMCB.2011.2162400
    [4] Shukla D, Ghorai SK. Development of a low cost real time strain monitoring system using DSP technique. Proceedings of 2011 International Conference on Multimedia, Signal Processing and Communication Technologies. Aligarh, India. 2011.1–4.
    [5] 曹燕, 李欢, 王天宝. 基于深度学习的目标检测算法研究综述. 计算机与现代化, 2020, (5): 63–69. [doi: 10.3969/j.issn.1006-2475.2020.05.011
    [6] 王鸿斌, 张立毅. 新型神经网络的发展及其应用. 忻州师范学院学报, 2007, 23(2): 50–53. [doi: 10.3969/j.issn.1671-1491.2007.02.017
    [7] 马红强, 马时平, 许悦雷, 等. 基于深度卷积神经网络的低照度图像增强. 光学学报, 2019, 39(2): 0210004
    [8] Ren SQ, He KM, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137–1149. [doi: 10.1109/TPAMI.2016.2577031
    [9] Uijlings JRR, van de Sande KEA, Gevers T, et al. Selective search for object recognition. International Journal of Computer Vision, 2013, 104(2): 154–171. [doi: 10.1007/s11263-013-0620-5
    [10] Felzenszwalb PF, Girshick RB, McAllester D, et al. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627–1645. [doi: 10.1109/TPAMI.2009.167
    [11] 晏琳, 景军锋, 李鹏飞. Faster RCNN模型在坯布疵点检测中的应用. 棉纺织技术, 2019, 47(2): 24–27. [doi: 10.3969/j.issn.1001-7415.2019.02.006
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

蔡兆信,李瑞新,戴逸丹,潘家辉.基于Faster RCNN的布匹瑕疵识别系统.计算机系统应用,2021,30(2):83-88

复制
分享
文章指标
  • 点击次数:1048
  • 下载次数: 2490
  • HTML阅读次数: 2534
  • 引用次数: 0
历史
  • 收稿日期:2020-06-18
  • 最后修改日期:2020-07-14
  • 在线发布日期: 2021-01-29
文章二维码
您是第10783221位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号