融合选择核注意力的无纺布缺陷检测

doi:10.3778/j.issn.1002-8331.2308-0182

摘要/Abstract

摘要： 针对无纺布缺陷检测算法实时性差，检测准确率低的问题，设计了一种基于改进YOLOv5的无纺布缺陷检测算法N-YOLO。该算法结合产线实际情况和产品特性运用视觉检测技术，在YOLOv5算法的基础上引入FasterNet网络作为主干特征提取网络进行轻量化改进，利用部分卷积进行特征提取减少模型计算量。同时在C3模块中增加SK注意力机制提高模型检测精度，并采用WIoUv1损失函数计算边界框回归损失，提高边界框定位精度。实验结果表明N-YOLO算法与YOLOv5s相比浮点计算量减少85.4%，参数量由7?020?913减少到3?368?105，减少了52%，模型大小为6.63?MB，平均检测精度能达到99.2%，召回率达到99.2%，与Faster R-CNN和SSD等目标检测算法相比具有明显优势，无需昂贵的硬件设备即可在高速生产情况下对无纺布缺陷进行实时检测。

关键词: YOLOv5, 缺陷检测, 轻量化, 注意力机制, 损失函数

Abstract: Aiming at the problems of poor real-time performance and low detection accuracy of non-woven defect detection algorithm, a non-woven defect detection algorithm N-YOLO based on improved YOLOv5 is designed. Based on the actual situation of the production line and product characteristics, the algorithm uses visual detection technology. Firstly, based on the YOLOv5 algorithm, FasterNet network is introduced as the backbone feature extraction network for lightweight improvement, and partial convolution is used for feature extraction to reduce the model computation. At the same time, SK attention mechanism is added in C3 module to improve the model detection accuracy, and WIoUv1 loss function is used to calculate the boundary frame regression loss to improve the boundary frame positioning accuracy. Experimental results show that compared with YOLOv5, N-YOLO algorithm reduces floating point computation by 85.4%, parameter number by 52% from 7 020 913 to 3 368 105, model size is 6.63 MB, average detection accuracy can reach 99.2%, recall rate can reach 99.2%. Compared with target detection algorithms such as Faster R-CNN and SSD, it has obvious advantages, and can detect defects of non-wovens in real time under high-speed production without expensive hardware equipment.

Key words: YOLOv5, defect detection, lightweight, attention mechanism, loss function

陆芸婷, 康绍鹏, 吴双, 何川. 融合选择核注意力的无纺布缺陷检测[J]. 计算机工程与应用, 2024, 60(24): 331-339.

LU Yunting, KANG Shaopeng, WU Shuang, HE Chuan. Nonwoven Defect Detection by Fusing Selection Kernel Attention[J]. Computer Engineering and Applications, 2024, 60(24): 331-339.

参考文献

[1] 钟自创. 我国无纺布主流技术与其应用研究[J]. 造纸装备及材料, 2020, 49(2): 76.
ZHONG Z C. Research on mainstream nonwoven technologies and their applications in China[J]. Papermaking Equipment and Materials, 2020, 49(2): 76.
[2] 吕文涛, 林琪琪, 钟佳莹, 等. 面向织物疵点检测的图像处理技术研究进展[J]. 纺织学报, 2021, 42(11): 197-206.
Lü W T, LIN Q Q, ZHONG J Y, et al. Research progress of image processing technology for fabric defect detection[J]. Journal of Textile Research, 2021, 42(11): 197-206.
[3] ABOUELELA A, ABBAS H M, ELSEEB H, et al. Automated vision system for localizing structural defects in textile fabrics[J]. Pattern Recognition Letters, 2005, 26(10): 1435-1443.
[4] LI C, GAO G, LIU Z, et al. Defect detection for patterned fabric images based on GHOG and low-rank decomposition[J]. IEEE Access, 2019, 7: 83962-83973.
[5] GUSTIAN D A, ROHMAH N L, SHIDI K G F, et al. Classification of troso fabric using SVM-RBF multi-class method with GLCM and PCA feature extraction[C]//Proceedings of the 2019 International Seminar on Application for Technology of Information and Communication (iSemantic), 2019: 7-11.
[6] REBHI A, ABID S, FNAIECH F. Fabric defect detection using local homogeneity and morphological image processing[C]//Proceedings of the 2016 International Image Processing, Applications and Systems (IPAS), 2016: 1-5.
[7] PAN Z, HE N, JIAO Z. FFT used for fabric defect detection based on CUDA[C]//Proceedings of the 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2017: 2104-2107.
[8] LI Y H, ZHOU X Y. Fabric defect detection with optimal Gabor wavelet based on radon[C]//Proceedings of the 2020 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS), 2020: 788-793.
[9] 曹桂红, 欧阳颖, 国庆, 等. 基于SIFT算法的织物疵点检测[J]. 信息记录材料, 2019, 20(9): 79-81.
CAO G H, OUYANG Y, GUO Q, et al. Fabric defect detection based on SIFT algorithm[J]. Information Recording Materials, 2019, 20(9): 79-81.
[10] 杨晓波. 基于GMＲF模型的统计特征畸变织物疵点识别[J]. 纺织学报, 2013, 34(4): 137-142.
YANG X B. Fabric defect detection of statistic aberration feature based on GMRF model[J]. Journal of Textile Research, 2013, 34(4): 137-142.
[11] 陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述[J]. 自动化学报, 2021, 47(5): 1017-1034.
TAO X, HOU W, XU D. A survey of surface defect detection methods based on deep learning[J]. Journal of Automatica Sinica, 2021, 47(5): 1017-1034.
[12] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015.
[13] 王琳毅, 白静, 李文静, 等. YOLO系列目标检测算法研究进展[J]. 计算机工程与应用, 2023, 59(14): 15-29.
WANG L Y, BAI J, LI W J, et al. Research progress of YOLO series target detection algorithms[J]. Computer Engineering and Applications, 2023, 59(14): 15-29.
[14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, The Netherlands, 2016: 21-37.
[15] 邵延华, 张铎, 楚红雨, 等. 基于深度学习的YOLO目标检测综述[J]. 电子与信息学报, 2022, 44(10): 3697-3708.
SHAO Y H, ZHANG D, CHU H Y, et al. A review of YOLO object detection based on deep learning[J]. Journal of Electronics and Information Technology, 2022, 44(10): 3697-3708.
[16] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[17] CHEN J R, KAO S H, HAO H E, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12021-12031.
[18] LI X, WANG W, HU X L, et al. Selective kernel networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 510-519.
[19] ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[20] TONG Z J, CHEN Y H, XU Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[21] HENDRYCKS D, GIMPEL K. Gaussian error linear units (gelus)[J]. arXiv:1606.08415, 2016.
[22] GUO M H, XU T X, LIU J J, et al. Attention mechanisms in computer vision: a survey[J]. Computational Visual Media, 2022, 8(3): 331-368.