改进YOLOv5的织物疵点检测算法

doi:10.3778/j.issn.1002-8331.2209-0413

摘要/Abstract

摘要： 针对目前应用到织物疵点检测的网络模型中存在的两阶段算法检测速度慢、一阶段算法检测精度低的问题，提出了一种改进YOLOv5的织物疵点检测算法。针对织物疵点大小不一的问题，对[K]-mean算法的聚类距离标准进行修改，重新计算先验框大小；对网络Neck层标准卷积（standard convolution，SC）进行改进，将深度分离卷积（depth separation convolution，DSC）与标准卷积结合，减少网络层参数量，同时保持网络的特征提取能力；在特征融合阶段引入坐标注意力机制（coordinate attention，CA），使网络能够捕捉各通道之间联系的同时保留目标的精确定位信息，加强网络的特征提取和定位能力；使用加权双向特征金字塔网络（bidirectional feature pyramid network，BiFPN）中的方法，对特征金字塔模块进行修改，实现简单快速的多尺度特征融合。在数据集上进行训练，结果表明，改进的YOLOv5模型的mAP值可达到97.4%，相比于原网络精度提高了2.8个百分点，满足了织物疵点检测的要求。

关键词: 织物疵点检测, YOLOv5, 注意力机制, 特征融合

Abstract: Aiming at the problems of slow detection speed of two-stage algorithm and low detection accuracy of one-stage algorithm in the current network model applied to fabric defect detection, an improved YOLOv5 fabric defect detection algorithm is proposed. Firstly, for the different sizes of fabric defects, the clustering distance standard of the [K]-mean algorithm is modified, and the size of the priori frame is recalculated. Secondly, the standard convolution（SC） of the network Neck layer is improved, and the depth separation convolution（DSC） is combined with the standard convolution to reduce the amount of network layer parameters while maintaining the feature extraction capability of the network. The coordinate attention（CA） mechanism is introduced in the feature fusion stage, so that the network can capture the connection between each channel while retaining the precise positioning information of the target, thereby enhancing the feature extraction and positioning capabilities of the network. Finally, the weighted bidirectional feature pyramid network（BiFPN） is used, the feature pyramid module is modified to achieve simple and fast multi-scale feature fusion. After training on the data set, the results show that the mAP value of the improved YOLOv5 model can reach 97.4%, which is 2.8 percentage points higher than the original network accuracy, which meets the requirements of fabric defect detection.

Key words: fabric defect detection, YOLOv5, attention mechanism, feature fusion

马阿辉, 祝双武, 李丑旦, 马晓彤, 王世豪. 改进YOLOv5的织物疵点检测算法[J]. 计算机工程与应用, 2023, 59(10): 244-252.

MA Ahui, ZHU Shuangwu, LI Choudan, MA Xiaotong, WANG Shihao. Improved Fabric Defect Detection Algorithm of YOLOv5[J]. Computer Engineering and Applications, 2023, 59(10): 244-252.

参考文献

[1] KUMAR A.Computer vision based fabric defect detection：a survey[J].IEEE Transactions on Industrial Electronics，2008，55：348-363.
[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.
LV W T，LIN Q Q，ZHONG J Y，et al.Research progress of image processing technology for fabric defect detection[J].Journal of Textiles，2021，42（11）：197-206.
[3] 张露，朱文俊，祝双武.织物疵点自动检测方法及应用进展[J].纺织科技进展，2022（2）：21-26.
ZHANG L，ZHU W J，ZHU S W.The method and application progress of automatic detection of fabric defects[J].Progress in Textile Science and Technology，2022（2）：21-26.
[4] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[5] GIRSHICK R.Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision，2015：1440-1448.
[6] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28，2015.
[7] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//14th European Conference on Computer Vision.Cham：Springer，2016：21-37.
[8] 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 J L，LU K.Dye-dyed fabric defect detection based on convolutional neural network and transfer learning[J].Shanghai Textile Technology，2019，47（6）：52-56.
[9] 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 H L，JING J F，ZHANG H H，et al.Fabric defect detection based on MF-SSD network[J].Cotton Textile Technology，2020，48（12）：11-16.
[10] JING J，ZHUO D，ZHANG H，et al.Fabric defect detection using the improved YOLOv3 model[J].Journal of Engineered Fibers and Fabrics，2020.DOI：10.1177/155892502
0908268.
[11] 陈梦琦，余灵婕，支超，等.融合注意力机制和Faster R-CNN的织物疵点检测算法[J].纺织高校基础科学学报，2021，34（4）：46-52.
CHEN M Q，YU L J，ZHI C，et al.Fabric defect detection algorithm integrating attention mechanism and Faster R-CNN[J].Journal of Basic Science of Textile Universities，2021，34（4）：46-52.
[12] HO C，CHOU W，SU E.Deep convolutional neural network optimization for defect detection in fabric inspection[J].Sensors（Basel），2021，21：7074.
[13] 叶舒婷，游思晴，郝灿，等.基于Cascade RCNN和二步聚类的织物疵点检测[J].棉纺织技术，2022，50（7）：24-29.
YE S T，YOU S Q，HAO C，et al.Fabric defect detection based on Cascade RCNN and two-step clustering[J].Cotton Textile Technology，2022，50（7）：24-29.
[14] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13713-13722.
[15] TAN M X，PANG R M，LE Q V.EfficientDet：scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10778-10787.
[16] HE K M，ZHANG X，REN S Q，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1904-1916.
[17] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[18] HU J，LI S，ALBANIE S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[19] WOO S H，PARK J C，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision，2018：3-19.
[20] CHOLLET F.Xception：deep learning with depthwise separable convolutions[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：1800-1807.
[21] SANDLER M，HOWARD A G，ZHU M，et al.MobileNetV2：inverted residuals and linear bottlenecks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：4510-4520.
[22] MA N，ZHANG X，ZHENG H，SUN J.ShuffleNet V2：practical guidelines for efficient CNN architecture design[C]//Proceedings of the 15th European Conference on Computer Vision，2018.
[23] LI H，LI J，WEI H，et al.Slim-neck by GSConv：a better design paradigm of detector architectures for autonomous vehicles[J].arXiv：2206.02424，2022.