[1]刘兆英,陈志远,张　婷,等.改进YOLOv5的工业产品表面缺陷检测方法[J].郑州大学学报(工学版),2025,46(05):18-25.[doi:10.13705/j.issn.1671-6833.2025.02.020]
　LIU Zhaoying,CHEN Zhiyuan,ZHANG Ting,et al.Industrial Product Surface Defect Detection of Improved YOLOv5[J].Journal of Zhengzhou University (Engineering Science),2025,46(05):18-25.[doi:10.13705/j.issn.1671-6833.2025.02.020]
点击复制

改进YOLOv5的工业产品表面缺陷检测方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年05期
页码:
18-25
栏目:
出版日期:
2025-08-10

文章信息/Info

Title:
Industrial Product Surface Defect Detection of Improved YOLOv5
文章编号:
1671-6833(2025)05-0018-08
作者:
刘兆英1;  陈志远1;  张　婷1;  时亚南2;  陈迎春3
1.北京工业大学 计算机学院,北京 100124;2.新疆维吾尔自治区特种设备检验研究院 新疆特种设备检测技术研究重点实验室,新疆 乌鲁木齐 830011;3.北京工业大学 建筑工程学院,北京 100124
Author(s):
LIU Zhaoying1;  CHEN Zhiyuan1;  ZHANG Ting1;  SHI Yanan2;  CHEN Yingchun3
1.College of Computer Science, Beijing University of Technology, Beijing 100124, China; 2.Xinjiang Key Laboratory of Special Equipment Testing Technology, Xinjiang Uygur Autonomous Region Inspection Institute of Special Equipment, Urumqi 830011,China; 3.College of Architecture and Civil Engineering, Beijing University of Technology, Beijing 100124, China
关键词:
表面缺陷检测;  计算机视觉;  多尺度特征提取;  注意力机制;  解耦检测头
Keywords:
surface defect detection;  computer vision;  multi-scale feature extraction;  attention mechanism;  decoupling detection head
分类号:
TP391.4
DOI:
10.13705/j.issn.1671-6833.2025.02.020
文献标志码:
A
摘要:
针对工业场景下资源受限且表面缺陷图像对比度低的问题,提出了一种改进YOLOv5的工业产品表面缺陷检测方法。首先,在骨干网络中引入感受野增强模块,用于从不同层次的感受野提取更丰富的视觉特征;其次,在特征融合网络中添加混洗注意力模块,更有效地对不同维度的特征图进行融合;最后,采取了任务解耦检测头,使分类和回归两个任务采用相互独立的网络进行预测,降低彼此的干扰,提升检测精度。实验结果表明:该网络的参数量和计算量均低于YOLOX、YOLOv7、deformable DETR等模型,且在管道数字射线(DR)缺陷图像数据集PDD和NEU-DET数据集上,mAP@0.5分别提高2.23百分点和2.99百分点,兼顾了工业场景下对缺陷检测实时性和精确性的要求。
Abstract:
Aiming at the problem of limited resources and low contrast of surface defect images in industrial scenarios, an improved YOLOv5 industrial product surface defect detection method was proposed. This method first introduced a receptive field enhancement module in the backbone network to extract richer visual features from different levels of receptive fields. Secondly, a shuffle attention module was added to the feature fusion network to more effectively fuse feature maps of different dimensions. Finally, a task decoupling detection head was adopted, allowing the classification and regression tasks to use independent networks for prediction, reducing mutual interference and improving detection accuracy. The experimental results showed that the parameter and computational complexity of this network were lower than models such as YOLOX, YOLOv7, and deformable DETR. On the pipeline Digital Ray (DR) defect image dataset and NEU-DET dataset, the mAP@0.5 were increased by 2.23 percentage points and 2.99 percentage points respectively, balancing the requirements for real-time and accurate defect detection in industrial scenarios.

参考文献/References:

[1]CHEN Y J, DING Y Y, ZHAO F, et al. Surface defect detection methods for industrial products: a review[J]. Applied Sciences, 2021, 11(16): 7657. 

[2]罗东亮, 蔡雨萱, 杨子豪, 等. 工业缺陷检测深度学习方法综述[J]. 中国科学: 信息科学, 2022, 52(6): 1002-1039. 
LUO D L, CAI Y X, YANG Z H, et al. Survey on industrial defect detection with deep learning[J]. Scientia Sinica (Informationis), 2022, 52(6): 1002-1039. 
[3]REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. 
[4]CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018: 6154-6162. 
[5]HE K M, GKIOXARI G, DOLLÁR P, et al. Mask RCNN[C]∥2017 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2017: 2980-2988. 
[6]LIU Y X, WU D B, LIANG J W, et al. Aeroengine blade surface defect detection system based on improved Faster RCNN[J]. International Journal of Intelligent Systems, 2023, 2023: 1992415. 
[7]WEI B, HAO K R, GAO L, et al. Detecting textile micro-defects: a novel and efficient method based on visual gain mechanism[J]. Information Sciences, 2020, 541: 60-74. 
[8]LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[EB/OL].(2015-12-08)[202411-06].https:∥doi.org/10.48550/arXiv.1512.02325. 
[9]LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]∥2017 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2017: 2999-3007. 
[10] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE, 2016: 779-788. 
[11] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517-6525. 
[12] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL].(2018-04-08)[2024-11-06].https:∥doi.org/10.48550/arXiv.1804.02767. 
[13] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection [EB/OL].(2020-04-23)[2024-11-06]. https:∥doi. org/10.48550/arXiv.2004.10934. 
[14] LI C, LI L, JIANG H, et al. Yolov6: a single-stage object detection framework for industrial applications[EB/ OL]. (2022-09-01)[2024-11-06].https:∥doi. org/ 10.48550/arXiv.2209.02976. 
[15]WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-theart for real-time object detectors[C]∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2023: 7464-7475. 
[16] ZHANG J D, XU J B, ZHU L Y, et al. An improved MobileNet-SSD algorithm for automatic defect detection on vehicle body paint[J]. Multimedia Tools and Applications, 2020, 79(31): 23367-23385. 
[17] PAN K L, HU H Y, GU P. WD-YOLO: a more accurate YOLO for defect detection in weld X-ray images[J]. Sensors, 2023, 23(21): 8677. 
[18] LIU M Y, CHEN Y P, XIE J M, et al. LF-YOLO: a lighter and faster YOLO for weld defect detection of X-ray image[J]. IEEE Sensors Journal, 2023, 23(7): 7430-7439. 
[19]张震, 陈可鑫, 陈云飞. 优化聚类和引入CBAM的YOLOv5管制刀具检测[J]. 郑州大学学报(工学版), 2023, 44(5): 40-45, 61. 
ZHANG Z, CHEN K X, CHEN Y F. YOLOv5 with optimized clustering and CBAM for controlled knife detection [J]. Journal of Zhengzhou University (Engineering Science), 2023, 44(5): 40-45, 61. 
[20]魏明军, 王镆涵, 刘亚志, 等. 基于特征融合和混合注意力的小目标检测[J]. 郑州大学学报(工学版), 2024, 45(3): 72-79. 
WEI M J, WANG M H, LIU Y Z, et al. Small object detection based on feature fusion and mixed attention[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(3): 72-79.
[21] XIE Y F, HU W T, XIE S W, et al. Surface defect detection algorithm based on feature-enhanced YOLO[J]. Cognitive Computation, 2023, 15(2): 565-579. 
[22] GUO Z X, WANG C S, YANG G, et al. MSFT-YOLO: improved YOLOv5 based on transformer for detecting defects of steel surface[J]. Sensors, 2022, 22(9): 3467. 
[23]WANG C Y, MARK LIAO H Y, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2020: 1571-1580. 
[24] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018: 8759-8768. 
[25] ELFWING S, UCHIBE E, DOYA K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning[J]. Neural Networks, 2018, 107: 3-11. 
[26]时亚南, 陈志远, 刘兆英, 等. 改进YOLOv5n的管道DR缺陷图像检测方法[J]. 计算机工程与应用, 2024, 60(12): 366-372. 
SHI Y N, CHEN Z Y, LIU Z Y, et al. Improved YOLOv5n pipeline DR defect image detection method [J]. Computer Engineering and Applications, 2024, 60 (12): 366-372. 
[27] HE Y, SONG K C, MENG Q G, et al. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(4): 1493-1504. 
[28] GE Z, LIU S T, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL].(2021-07-18)[202411-06].https:∥arxiv.org/abs/2107.08430. 
[29] ZHU X Z, SU W J, LU L W, et al. Deformable DETR: deformable transformers for end-to-end object detection [EB/OL].(2020-10-08)[2024-11-06]. https:∥doi. org/10.48550/arXiv.2010.04159. 
[30]WANG C Y, YEH I H, LIAO H Y M. YOLOv9: learning what you want to learn using programmable gradient information[EB/OL].(2024-02-21)[2024-11-06]. https:∥doi.org/10.48550/arXiv.2402.13616. 
[31] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2020: 10778-10787.

相似文献/References:

[1]董汉莉..Marr-Hildreth算子边缘精确定位的研究[J].郑州大学学报(工学版),1999,20(02):36.[doi:10.3969/j.issn.1671-6833.1999.02.012]
　DONG Hanli..A study of the precise positioning of the edge of the Marr-Hildreth operator[J].Journal of Zhengzhou University (Engineering Science),1999,20(05):36.[doi:10.3969/j.issn.1671-6833.1999.02.012]

更新日期/Last Update: 2025-09-19