|本期目录/Table of Contents|

[1]郭波,吕文涛,余序宜,等.基于改进YOLOv5模型的织物疵点检测算法[J].浙江理工大学学报,2022,47-48(自科五):755-763.
 GUO Bo,LV Wentao,YU Xuyi,et al.Fabric defect detection algorithm based on improved YOLOv5 Model[J].Journal of Zhejiang Sci-Tech University,2022,47-48(自科五):755-763.
点击复制

基于改进YOLOv5模型的织物疵点检测算法()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第47-48卷
期数:
2022年自科第五期
页码:
755-763
栏目:
出版日期:
2022-09-10

文章信息/Info

Title:
Fabric defect detection algorithm based on improved YOLOv5 Model
文章编号:
1673-3851 (2022) 09-0755-09
作者:
郭波吕文涛余序宜郭庆陈亮亮王成群
1.浙江理工大学信息学院,杭州 310018;2.浙江省技术创新服务中心,杭州 310007;3.浙江经贸职业技术学院应用工程系,杭州 310018
Author(s):
GUO BoLV Wentao YU Xuyi GUO Qing CHEN Liangliang WANG Chengqun
1.School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China; 2. Zhejiang Technical Innovation Service Center, Hangzhou 310007, China; 3.Department of Applied Engineering, Zhejiang Institute of Economics and Trade, Hangzhou 310018, China
关键词:
深度学习YOLOv5织物疵点检测激活函数实时检测
分类号:
TS107; TP202
文献标志码:
A
摘要:
针对织物疵点存在的种类多、密集度高、尺度小等检测难点,提出一种基于改进YOLOv5模型的织物疵点检测算法。首先,通过 K means++方法对所有真实框进行聚类,提高了模型训练时的收敛速度;其次,将Mish激活函数用于模型训练,提高了其非线性表达能力;再次,通过增加检测层提升了对多尺度目标的检测性能,并调整池化层位置提取多尺度的特征信息,提升了算法的鲁棒性及检测精度;最后,优化颈部网络结构,提升了算法的检测精度和速度。基于天池织物疵点数据集的实验结果表明:该算法的mAP达到了76.8%,相较基于原YOLOv5模型的织物疵点检测算法提升了7.7%,验证了该算法的有效性和鲁棒性。该算法在满足实时检测的要求下提高了检测精度,并优于其他主流目标检测算法,具有良好的应用前景。

参考文献/References:

[1]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.

[2]Xie H S, Zhang Y F, Wu Z S. Fabric defect detection method combing image pyramid and direction template[J]. IEEE Access, 2019, 7: 182320-182334.

[3]郑雨婷, 王成群, 陈亮亮, 等. 基于卷积神经网络的织物图像识别方法研究进展. 现代纺织技术.(2022-02-24)[2022-04-28].

[4]Zhai S P, Shang D R, Wang S H, et al. DFSSD: An improved SSD object detection algorithm based on DenseNet and feature fusion[J]. IEEE Access, 2020, 8: 24344-24357.

[5]Fang W, Wang L, Ren P M. Tinier YOLO: A real time object detection method for constrained environments[J]. IEEE Access, 2019, 8: 1935-1944.

[6]Kim C, Kim H M, Lyuh C G, et al. Implementation of yolo v2 image recognition and other testbenches for a CNN accelerator[C]//2019 IEEE 9th International Conference on Consumer Electronics. Berlin, Germany: IEEE, 2019: 242-247.

[7]Redmon J, Farhadi A. YOLOv3: An incremental improvement. (2018-04-08)[2022-02-24].

[8]Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection. (2020-4-23)[2022-02-24].

[9]Jocher G. Yolov5. (2020-7-24)[2022-02-24]

[10]张静, 农昌瑞, 杨智勇. 基于卷积神经网络的目标检测算法综述[J/OL]. 兵器装备工程学报. (2022-04-28)[2022-04-29].

undefined

相似文献/References:

[1]邓远远,沈炜.基于注意力反馈机制的深度图像标注模型[J].浙江理工大学学报,2019,41-42(自科二):208.
 DENG Yuanyuan,SHEN Wei.Depth image caption model based on  attention feedback mechanism[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科五):208.
[2]包晓安,徐海,张娜,等.基于深度学习的语音识别模型及其在智能家居中的应用[J].浙江理工大学学报,2019,41-42(自科二):217.
 BAO Xiaoan,XU Hai,ZHANG Na,et al.Speech recognition model based on deep learning and its application in smart home[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科五):217.
[3]邓远远,沈炜.基于注意力反馈机制的深度图像标注模型[J].浙江理工大学学报,2019,41-42(自科二):208.
 DENG Yuanyuan,SHEN Wei.Depth image caption model based on attention feedback mechanism[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科五):208.
[4]陈巧红,董雯,孙麒,等.基于混合神经网络的单文档自动文摘模型[J].浙江理工大学学报,2019,41-42(自科四):489.
 CHEN Qiaohong,DONG Wen,SUN Qi,et al.Single document automatic summarization model based on hybrid neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科五):489.
[5]包晓安,高春波,张娜,等.基于生成对抗网络的图像超分辨率方法[J].浙江理工大学学报,2019,41-42(自科四):499.
 BAO Xiaoan,GAO Chunbo,ZHANG Na,et al.Image superresolution method based ongenerative adversarial network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科五):499.
[6]陈巧红,陈翊,孙麒,等.服装图像分类技术综述[J].浙江理工大学学报,2019,41-42(自科五):631.
 CHEN Qiaohong,CHEN Yi,SUN Qi,et al.Overview of clothing image classification technology[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科五):631.
[7]包晓安,涂小妹,徐璐,等.基于扩展卷积神经网络与度量学习的指静脉识别[J].浙江理工大学学报,2020,43-44(自科二):232.
 BAO Xiaoan,TU Xiaomei,XU Lu,et al.Finger vein recognition based on extended convolutional neural networks and metric learning[J].Journal of Zhejiang Sci-Tech University,2020,43-44(自科五):232.
[8]潘海鹏,郝慧,苏雯.基于注意力机制与多尺度特征融合的人脸表情识别[J].浙江理工大学学报,2022,47-48(自科三):382.
 PAN Haipeng,HAO Hui,SU Wen.Facial expression recognition based on attention mechanism and multiscale feature fusion[J].Journal of Zhejiang Sci-Tech University,2022,47-48(自科五):382.
[9]廖龙杰,吕文涛,叶冬,等.基于深度学习的小目标检测算法研究进展[J].浙江理工大学学报,2023,49-50(自科三):331.
 LIAO Longjie,L Wentao,YE Dong,et al.Research progress of small target detection based on deep learning[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科五):331.
[10]任瀚实,周志宇,孙树森.基于通道注意力机制的室内场景深度图补全[J].浙江理工大学学报,2023,49-50(自科三):344.
 REN Hanshi,ZHOU Zhiyu,SUN Shusen.Depth map completion for indoor scenes based on the channel attention mechanism[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科五):344.

备注/Memo

备注/Memo:
收稿日期: 2022-02-24
网络出版日期:2022-06-02
基金项目: 国家自然科学基金项目(61601410);浙江省科技厅重点研发计划项目(2021C01047, 2022C01079)
作者简介: 郭波(1996-),男,杭州人,硕士研究生,主要从事计算机视觉方面的研究
通信作者: 吕文涛,E-mail:alvinlwt@zstu.edu.cn
更新日期/Last Update: 2022-09-07