Research progress of fabric image processing methods based on convolutional neural network

doi:10.19398/j.att.202110050

Abstract

Abstract: Fabric image recognition technology based on convolutional neural network has the advantages of autonomous learning, high accuracy and wide applicability, and has been widely used in textile industry production. This paper reviews the specific applications and research progress of defect classification, defect detection, image classification and image segmentation technology based on convolutional neural networks in the textile field. This article summarizes the improvement points, advantages and disadvantages of various network structures, and at the same time looks forward to the future research directions regarding the current problems. With the continuous optimization of network structure, image recognition methods have their own emphasis on real-time and accuracy, but their robustness and applicability still have a lot of room for development, and further research is needed.

Key words: convolutional neural network, image identification, defect classification, defect detection, image classification

摘要： 基于卷积神经网络的织物图像识别技术具有自主学习、准确率高和适用性广的优点,已被广泛应用于纺织工业生产中。本文面向纺织领域详细综述了基于卷积神经网络的疵点分类、瑕疵检测、图像分类、图像分割技术的具体应用和研究进展,总结了各种网络结构的改进点和优缺点,同时就目前存在的问题及未来研究方向进行了展望。随着网络结构的不断优化,图像识别方法对实时性和精确性各有侧重,但其鲁棒性和适用性仍有较大的发展空间,有待做进一步研究。

关键词: 卷积神经网络, 图像识别, 疵点分类, 瑕疵检测, 图像分类

CLC Number:

TS107
TP183

ZHENG Yuting, WANG Chengqun, CHEN Liangliang, WU Jiang, LÜ Wentao. Research progress of fabric image processing methods based on convolutional neural network[J]. Advanced Textile Technology, 2022, 30(5): 1-11.

郑雨婷, 王成群, 陈亮亮, 吴江, 吕文涛. 基于卷积神经网络的织物图像识别方法研究进展[J]. 现代纺织技术, 2022, 30(5): 1-11.

References

[1] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[2] 晏琳.坯布表面缺陷的检测与分类算法研究[D].西安:西安工程大学,2019.
YAN Lin. Research on Fabric Surface Defect Detection and Classification[D]. Xi'an: Xi'an Polytechnic University, 2019.
[3] 李敏,杨珊,何儒汉,等.结合视觉显著性和卷积神经网络的提花织物疵点检测技术[J].现代纺织技术,2021,29(6):62-66.
LI Min, YANG Shan, HE Ruhan, et al. Jacquard fabric defect detection combining visual saliency and convolutional neural network[J]. Advanced Textile Technology, 2021,29(6):62-66.
[4] 江伴,谢晓峰,董燕.基于浅层卷积特征和双低秩表示的织物疵点检测算法研究[J].中原工学院学报,2020,31(5):21-26.
JIANG Ban, XIE Xiaofeng, DONG Yan. Fabric defect detection algorithm based on shallow CNN feature and double low-rank representation[J]. Journal of Zhongyuan University of Technology, 2020, 31(5): 21-26.
[5] CHOLLET F. Xception: Deep learning with depthwise separable convolutions[C]// IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. IEEE, 2017: 1251-1258.
[6] 史甜甜.基于Fisher准则的深层卷积神经网络织物疵点检测[J].计算机系统应用,2019,28(3):140-145.
SHI Tiantian. Deep convolutional neural network fabric defect detection based on fisher criterion[J]. Computer Systems and Applications, 2019, 28(3): 140-145.
[7] LIU Z, ZHANG C, LI C, et al. Fabric defect recognition using optimized neural networks[J]. Journal of Engineered Fibers and Fabrics, 2019, 14: 1558925019897396.
[8] SZEGEDY C, LIU W, JIA Y, et al.Going deeper with convolutions[C]// IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA. IEEE, 2015: 1-9.
[9] 赵志勇,叶林,桑红石,等.深度学习在布匹缺陷检测中的应用[J].国外电子测量技术,2019,38(8):110-116.
ZHAO Zhiyong, YE Lin, SANG Hongshi, et al. Application of deep learning in fabric defect detection[J]. Foreign Electronic Measurement Technology, 2019, 38(8): 110-116.
[10] 王理顺,钟勇,李振东,等.基于深度学习的织物缺陷在线检测算法[J].计算机应用,2019,39(7):2125-2128.
WANG Lishun, ZHONG Yong, LI Zhendong, et al. Online fabric defect recognition algorithm based on deep learning[J]. Journal of Computer Applications, 2019, 39(7): 2125-2128.
[11] SZEGEDY C, VANHOUCKE V, LOFFE S, et al. Rethinking the inception architecture for computer vision[C]// IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA. IEEE, 2016: 2818-2826.
[12] 曹振军,景军锋,苏泽斌,等.基于树莓派的深度学习色织物疵点检测研究[J].棉纺织技术,2019,47(1):11-15.
CAO Zhenjun, JING Junfeng, SU Zebin, et al. Study on the defect detection of yarn-dyed fabric with deep learning based on raspberry pi[J]. Cotton Textile Technology, 2019, 47(1): 11-15.
[13] 罗俊丽,路凯.基于卷积神经网络和迁移学习的色织物疵点检测[J].上海纺织科技,2019,47(6):52-56.
LUO Junli, LU Kai. Yarn-dyed fabric defect detection based on convolution neural network and transfer learning[J]. Shanghai Textile Science and Technology, 2019, 47(6): 52-56.
[14] 蔡鹏,杨磊,罗俊丽.一种基于卷积神经网络模型融合的织物疵点检测方法[J].北京服装学院学报(自然科学版),2020,40(1):55-62.
CAI Peng, YANG Lei, LUO Junli. Fabric defet detection method based on fusion of convolutional neural network models[J]. Journal of Beijing Institute of Fashion Technology(Natural Science Edition), 2020, 40(1): 55-62.
[15] 罗维平,徐洋,陈永恒,等.基于迁移学习和改进ResNet50网络的织物疵点检测算法[J].毛纺科技,2021,49(2):71-78.
LUO Weiping, XU Yang, CHEN Yongheng, et al. Fabric defect detection algorithm based on migration learning and improved ResNet50 network[J]. Wool Textile Journal, 2021, 49(2): 71-78.
[16] 崔春杰,景浩田,尹中信.深度学习算法在织物疵点识别中的应用研究[J].化纤与纺织技术,2021,50(1):69-71.
CUI Chunjie, JING Haotian, YIN Zhongxin. Research on the application of deep learning algorithms in fabric defect recognition[J]. Chemical Fiber and Textile Technology, 2021, 50(1): 69-71.
[17] 刘艳锋,郑云波,黄惠玲,等.基于卷积神经网络的织物瑕疵检测方法研究[J].信息技术与网络安全,2020,39(11):62-68.
LIU Yanfeng, ZHENG Yunbo, HUANG Huiling, et al. Research on fabric defect detection method based on convolutional neural network[J]. Artificial intelligence and security, 2020, 39(11): 62-68.
[18] 苏泽斌,高敏,李鹏飞,等.基于卷积神经网络的数码印花缺陷分类算法[J].激光与光电子学进展,2020,57(24):136-144.
SU Zebin, GAO Min, LI Pengfei, Digital printing defect classification algorithm based on convolutional neural network[J]. Laser and Optoelectronics Progress, 2020, 57(24): 136-144.
[19] 张敏,赵雪青.基于EfficientNets的织物疵点图像分类方法[J].纺织高校基础科学学报,2020,33(4):64-70.
ZHANG Min, ZHAO Xueqing. EfficientNets-based method for fabric defect image classification[J]. Basic Sciences Journal of Textile Universities, 2020, 33(4): 64-70.
[20] 孙羽,何志勇,张浩,等.基于DCNN的布匹疵点检测方法[J].中国科技信息,2021(2):92-95.
SUN Yu, HE Zhiyong, ZHANG Hao, et al. DCNN-based cloth defect detection method[J]. China Science and Technology Information, 2021(2): 92-95.
[21] 李明,景军锋,李鹏飞.应用GAN和FasterR-CNN的色织物缺陷识别[J].西安工程大学学报,2018,32(6):663-669.
LI Ming, JING Junfeng, LI Pengfei. Yarn-dyed fabric defect detection based on GAN and Faster RCNN[J]. Journal of Xi'an Polytechnic University, 2018, 32(6): 663-669.
[22] 安萌,郑飂默,王诗宇,等.一种改进FasterR-CNN的面料疵点检测方法[J].小型微型计算机系统,2021,42(5):1029-1033.
AN Meng, ZHENG Liaomo, WANG Shiyu, et al. Fabric defect detection method based on improved Faster R-CNN[J]. Journal of Chinese Computer Systems, 2021, 42(5): 1029-1033.
[23] 陈康,朱威,任振峰,等.基于深度残差网络的布匹疵点检测方法[J].小型微型计算机系统,2020,41(4):800-806.
CHEN Kang, ZHU Wei, REN Zhenfeng, et al. Fabric defect detection method based on deep residual network[J]. Journal of Chinese Computer Systems, 2020, 41(4): 800-806.
[24] 晏琳,景军锋,李鹏飞.FasterRCNN模型在坯布疵点检测中的应用[J].棉纺织技术,2019,47(2):24-27.
YAN Lin, JING Junfeng, LI Pengfei. Application of Faster RCNN mold used in gray fabric defect detection[J]. Cotton Textile Technology, 2020, 41(4): 800-806.
[25] ZHOU H, JANG B, CHEN Y, et al. Exploring faster RCNN for fabric defect detection[C]// Third International Conference on Artificial Intelligence for Industries (AI4I). Irvine, CA, USA. IEEE, 2020: 52-55.
[26] 廖如天.基于深度学习的异常目标识别[D].南京:东南大学,2019.
LIAO Rutian. Anomaly Object Detection Based on Deep learning[D]. Nanjing: Southeast University, 2019.
[27] REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. arXiv, 2018: 1804.02767[cs.CV]. https://arxiv.org/abs/1804.02767.
[28] 彭亚楠.基于深度学习的织物疵点检测研究[D].赣州:江西理工大学,2020.
PENG Yanan. Research on Fabric Defect Detection Based on Deep Learning[D]. Ganzhou: Jiangxi University of Science and Technology.
[29] 谢景洋,王巍,刘婷.基于YOLOv3算法的不同主干网络对织物瑕疵检测[J].测控技术,2021,40(3):61-66,95.
XIE Jingyang, WANG Wei, LIU Ting. Fabric surface defect detection based on YOLO v3 with different backbone networks[J]. Measurement and Control Technology, 2021, 40(3): 61-66, 95.
[30] 崔健.基于快速轻量卷积神经网络的织物缺陷检测算法研究[D].郑州:中原工学院,2020.
CUI Jian. Researh on Fabric Defect Detection Algorithm Based on Fast Lightweight Convolutional Neural Network[D]. Zhengzhou: Zhongyuan University of Technology, 2020.
[31] 黄汉林,景军锋,张缓缓,等.基于MF-SSD网络的织物疵点检测[J].棉纺织技术,2020,48(12):11-16.
HUANG Hanlin, JING Junfeng, ZHANG Huanhuan, et al. Fabric defect detection based on MF-SSD network[J]. Cotton Textile Technology, 2020, 48(12): 11-16.
[32] FU C Y, LIU W, RANGA A, et al. Dssd: Deconvolutional single shot detector[EB/OL]. arXiv, 2017: 1701.06659[cs.CV].https://arxiv.org/abs/1701.06659.
[33] 赵亚男,吴黎明,陈琦.基于多尺度融合SSD的小目标检测算法[J].计算机工程,2020,46(1):247-254.
ZHAO Yanan, WU Liming, CHEN Qi. Small object detection algorithm based on multi-scale fusion SSD[J]. Computer Engineering, 2020, 46(1): 247-254.
[34] 邓宇平,王桂棠.基于GoogLeNet网络与残差网络的织物纹理分析[J].电子测量技术,2021,44(7):31-38.
DENG Yuping, WANG Guitang. Fabric texture analysis based on GoogLeNet network and residual network[J]. Electronic Measurement Technology, 2021, 44(7): 31-38.
[35] SANDLER M, HOWARD A, ZHU M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT. IEEE, 2018: 4510-4520.
[36] 张玮,张华熊.基于卷积神经网络的纺织面料主成分分类[J].浙江理工大学学报(自然科学版),2019,41(1):1-8.
ZHANG Wei, ZHANG Huaxiong. Classification of main components of textile fabrics based on convolutional neural network[J]. Journal of Zhejiang Sci-Tech University(Natural Sciences Edition), 2019, 41(1): 1-8.
[37] 彭涛,彭迪,刘军平,等.基于图卷积神经网络的织物分类研究[J].计算机应用研究,2021,38(5):1581-1585,1594.
PENG Tao, PENG Di, LIU Junping, et al. Fabric classification based on graph convolutional network[J]. Application Research of Computers, 2021, 38(5): 1581-1585, 1594.
[38] YANG S, LIANG J, LIN M C. Learning-based cloth material recovery from video[C]// International Conference on Computer Vision. Venice. IEEE, 2017: 4383-4393.
[39] RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional Networks for Biomedical Image Segmentation[M]// Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015: 234-241.
[40] 汪坤,史伟民,李建强,等.基于深度学习的织物印花分割算法研究[J].现代纺织技术,2021,29(3):45-50.
WANG Kun, SHI Weimin, LI Jianqiang, et al. Research on fabric printing segmentation algorithm based on deep learning[J]. Advanced Textile Technology, 2021, 29(2): 45-50.
[41] 阿力木·安外尔,张大旭,何巍,等.基于深度学习的涂层织物折皱识别与检测[J].计算机工程与应用,2021,57(14):116-125.
ALIMAnwaier, ZHANG Daxu, HE Wei, et al. Deep learning-based crease detection and examination of coated fabrics[J]. Computer Engineering and Applications, 2021, 57(14): 116-125.