YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法

郭艳; 王智文; 赵润星

doi:10.12263/DZXB.20230772

您当前的位置：

首页 >

文章列表页 >

YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法

学术论文 | 更新时间：2025-12-24

- YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法
- YOLO-POD: High-Precision PCB Tiny-Defect Detection Algorithm Based on Multi-Dimensional Attention Mechanism
- 电子学报 2024年52卷第7期页码：2515-2528
- 作者机构：
  
  1.广西科技大学自动化学院，广西柳州 545616
  2.广西科技大学电子工程学院，广西柳州 545006
- 作者简介：
  
  [ "郭艳女，1997年7月出生于山西省忻州市.现为广西科技大学硕士研究生.研究方向为图像处理和目标检测.E-mail: 1655807007@qq.com" ]
  [ "王智文男，1969年1月出生于湖南省邵东市.现为广西科技大学教授.主要研究领域为机器学习与计算机视觉、移动目标检测与识别.主持与参与国家自然科学基金项目及广西自然科学基金项目等25项，在国内外公开发表研究论文173篇，被SCI或EI收录论文63篇.出版专著3部.E-mail: wzw69@gxust.edu.cn" ]
  [ "赵润星男，1998年10月出生于河南省洛阳市.现为广西科技大学硕士研究生.主要研究领域为图像处理和目标跟踪.E-mail: zrx_1998@163.com" ]
- 基金信息：
  
  国家自然科学基金(61962007;62266009);广西自然科学基金重点项目(2018GXNSFDA294001);广西财经大数据重点实验室开放基金(FEDOP2022A06)
- DOI：10.12263/DZXB.20230772
  中图分类号： TP391.4;TN41
- 收稿：2023-08-10，
  
  修回：2023-12-26，
  
  纸质出版：2024-07-25
- 稿件说明：
移动端阅览
郭艳, 王智文, 赵润星. YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法[J]. 电子学报, 2024, 52(07): 2515-2528.

GUO Yan, WANG Zhi-wen, ZHAO Run-xing. YOLO-POD: High-Precision PCB Tiny-Defect Detection Algorithm Based on Multi-Dimensional Attention Mechanism[J]. Acta Electronica Sinica, 2024, 52(07): 2515-2528.
郭艳, 王智文, 赵润星. YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法[J]. 电子学报, 2024, 52(07): 2515-2528. DOI：10.12263/DZXB.20230772

GUO Yan, WANG Zhi-wen, ZHAO Run-xing. YOLO-POD: High-Precision PCB Tiny-Defect Detection Algorithm Based on Multi-Dimensional Attention Mechanism[J]. Acta Electronica Sinica, 2024, 52(07): 2515-2528. DOI：10.12263/DZXB.20230772

摘要

随着电子设备的广泛应用，印刷电路板（Printed Circuit Board，PCB）在电子制造行业中具有重要意义.然而，由于制造过程中的不完美和环境因素的干扰，PCB上可能存在微小的缺陷.因此，开发高效准确的缺陷检测算法对于确保产品质量至关重要.针对PCB微小缺陷检测问题，本文提出了一种基于多维注意力机制的高精度PCB微小缺陷检测算法.为降低网络的模型参数量和计算量，引入部分卷积（Partial Convolution，PConv），将ELAN（Efficient Layer Aggregation Network）模块设计为更加高效的P-ELAN，同时，为增强网络对微小缺陷的特征提取能力，引入多维注意力机制（Multi-Dimensional Attention Mechanism，MDAM）的全维动态卷积（Omni-dimensional Dynamic Convolution，ODConv）并结合部分卷积，设计了POD-CSP（Partial ODconv-Cross Stage Partial）和POD-MP（Partial ODconv-Max Pooling）跨阶段部分网络模块，提出了OD-Neck结构.最后，本文基于（Youo Only Look Once version 7，YOLOv7）提出了对小目标更加高效的YOLO-POD模型，并在训练阶段采用一种新颖的Alpha-SIoU损失函数对网络进行优化.实验结果表明，YOLO-POD的检测精确率和召回率分别达到了98.31%和97.09%，并在多个指标上取得了领先优势，尤其是对于更严格的（mean Average Precision at IoU threshold of 0.75，mAP75）指标，比原始的YOLOv7模型提高28%.验证了YOLO-POD在PCB缺陷检测性能中具有较高的准确性和鲁棒性，满足高精度的检测要求，可为PCB制造行业提供有效的检测解决方案.

Abstract

With the widespread application of electronic devices

printed circuit boards (PCB) hold significant importance in the electronics manufacturing industry. However

due to imperfections in the manufacturing process and interference from environmental factors

tiny defects may in PCB. Therefore

the development of efficient and accurate defect detection algorithms is crucial in ensuring product quality. To address the challenge of detecting tiny defects on PCB

this paper proposes a high-precision PCB tiny defect detection algorithm based on multi-dimensional attention mechanism. To reduce model parameters and computational complexity

partial convolution (PConv) is introduced

and the ELAN module is redesigned as the more efficient P-ELAN. Additionally

to enhance the network’s feature extraction capability for tiny defects

the omni-dimensional dynamic convolution (ODConv) based on the multi-dimensional attention mechanism (MDAM) is introduced. By combining partial convolution

the POD-CSP (Partial ODConv-Cross Stage Partial) and POD-MP (Partial ODConv-Max Pooling) cross-stage partial network modules are designed

along with the OD-Neck structure. Finally

based on YOLOv7

a more efficient YOLO-POD model for small object detection is proposed

and the network is optimized during the training phase using a novel loss function called Alpha-SIoU. Experimental results demonstrate that YOLO-POD achieves a detection precision of 98.31% and recall rate of 97.09%

exhibiting substantial advantages across multiple metrics. Notably

it achieves a 28% improvement over the original YOLOv7 model

as to more stringent mAP75 metric. These results validate the high accuracy and robustness of YOLO-POD in PCB defect detection

fulfilling the requirements for high-precision detection and providing an effective detection solution for the PCB manufacturing industry.

关键词

Keywords

references

CHEN S Y , CHENG T H , FANG J M , et al . TinyDet: Accurately detecting small objects within 1 GFLOPs [J ] . Science China Information Sciences , 2022 , 66 ( 1 ): 119102 .

GE Z , LIU S T , WANG F , et al . YOLOX: Exceeding YOLO series in 2021 [EB/OL ] . ( 2021-07-18 )[ 2023-08-01 ] . http://arxiv.org/abs/2107.08430 http://arxiv.org/abs/2107.08430 .

CARINI A , RAMPONI G , MATHEWS V J . Nonlinear signal and image processing—A special issue in honour of Giovanni L. Sicuranza on his seventy-fifth birthday [J ] . EURASIP Journal on Advances in Signal Processing , 2017 , 2017 ( 1 ): 28 .

ZHU Y , LING Z G , ZHANG Y Q . Research progress and prospect of machine vision technology [J ] . Journal of Graphics , 2020 , 41 ( 6 ): 871 - 890 .

MALYUSKIN O , FUSCO V . Super-resolution defect characterization using microwave near-field resonance reflectometry and cross-correlation image processing [J ] . Sensing and Imaging , 2017 , 18 ( 1 ): 7 .

LIU W , ANGUELOV D , ERHAN D , et al . SSD: Single shot MultiBox detector [C ] // European Conference on Computer Vision . Cham : Springer , 2016 : 21 - 37 .

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 .

REDMON J , FARHADI A . YOLO9000: Better, faster, stronger [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 6517 - 6525 .

REDMON J , FARHADI A . YOLOv3: An incremental improvement [EB/OL ] . ( 2018-04-08 )[ 2023-08-01 ] . http://arxiv.org/abs/1804.02767 http://arxiv.org/abs/1804.02767 .

BOCHKOVSKIY A , WANG C Y , LIAO H Y M . YOLOv4: Optimal speed and accuracy of object detection [EB/OL ] . ( 2020-04-23 )[ 2023-08-01 ] . http://arxiv.org/abs/2004.10934 http://arxiv.org/abs/2004.10934 .

LI C Y , LI L L , JIANG H L , et al . YOLOv6: A single-stage object detection framework for industrial applications [EB/OL ] . ( 2022-09-07 )[ 2023-08-01 ] . https://arxiv.‍org/abs/2209.02976 https://arxiv.‍org/abs/2209.02976 .

WANG C Y , BOCHKOVSKIY A , LIAO H Y M . YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2023 : 7464 - 7475 .

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 . New York : ACM , 2014 : 580 - 587 .

GIRSHICK R . Fast R-CNN [C ] // 2015 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2015 : 1440 - 1448 .

REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: Towards real-time object detection with region proposal networks [C ] // NIPS’15: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 . New York : ACM , 2015 : 91 - 99 .

HE K M , GKIOXARI G , DOLLÁR P , et al . Mask R-CNN‍ [C ] // 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2017 : 2980 - 2988 .

HUANG G , LIU Z , VAN DER MAATEN L , et al . Densely connected convolutional networks [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 2261 - 2269 .

HUANG W B , WEI P . A PCB dataset for defects detection and classification [EB/OL ] . ( 2019-01-24 )[ 2023-08-01 ] . https://arxiv.org/abs/1901.08204 https://arxiv.org/abs/1901.08204 .

CHE X , ZHU W Z . Tile surface defect detection based on improved faster R-CNN [J ] . Academic Journal of Science and Technology , 2023 , 7 ( 1 ): 184 - 190 .

DING R W , DAI L H , LI G P , et al . TDD‐net: A tiny defect detection network for printed circuit boards [J ] . CAAI Transactions on Intelligence Technology , 2019 , 4 ( 2 ): 110 - 116 .

PENG C , LIU Y K , YUAN X P , et al . Research of image recognition method based on enhanced inception-ResNet-V2 [J ] . Multimedia Tools and Applications , 2022 , 81 ( 24 ): 34345 - 34365 .

CHEN I C , HWANG R C , HUANG H C . PCB defect detection based on deep learning algorithm [J ] . Processes , 2023 , 11 ( 3 ): 775 .

XIN H J , CHEN Z B , WANG B Y . PCB electronic component defect detection method based on improved YOLOv4 algorithm [J ] . Journal of Physics: Conference Series , 2021 , 1827 ( 1 ): 012167 .

WANG S , LU H , LU D , et al . PCB board defect detection based on lightweight artificial neural network [J ] . Instrumentation Science & Technology , 2022 , 50 ( 5 ): 98 - 104 .

YANG Y J , KANG H Y . An enhanced detection method of PCB defect based on improved YOLOv7 [J ] . Electronics , 2023 , 12 ( 9 ): 2120 .

WU D L , JIANG S , ZHAO E L , et al . Detection of camellia oleifera fruit in complex scenes by using YOLOv7 and data augmentation [J ] . Applied Sciences , 2022 , 12 ( 22 ): 11318 .

CHEN Z , LIU C , FILARETOV V , et al . Multi-scale ship detection algorithm based on YOLOv7 for complex scene SAR images [J ] . Remote Sensing , 2023 , 15 ( 8 ): 2071 .

WANG F H , JIANG J , CHEN Y , et al . Rapid detection of Yunnan Xiaomila based on lightweight YOLOv7 algorithm [J ] . Frontiers in Plant Science , 2023 , 14 : 1200144 .

LIU K Y , SUN Q , SUN D M , et al . Underwater target detection based on improved YOLOv7 [J ] . Journal of Marine Science and Engineering , 2023 , 11 ( 3 ): 677 .

王莹 , 王晶 , 高岚 , 等 . 一种注意力机制优化方法及硬件加速设计 [J ] . 电子学报 , 2023 , 51 ( 4 ): 1021 - 1029 .

WANG Y , WANG J , GAO L , et al . An improved attention mechanism algorithm model and hardware aceleration design method [J ] . Acta Electronica Sinica , 2023 , 51 ( 4 ): 1021 - 1029 . (in Chinese)

WOO S , PARK J , LEE J Y , et al . CBAM: Convolutional block attention module [C ] // European Conference on Computer Vision . Cham : Springer , 2018 : 3 - 19 .

JADERBERG M , SIMONYAN K , ZISSERMAN A , et al . Spatial transformer networks [EB/OL ] . ( 2015-06-05 )[ 2023-08-01 ] . http://arxiv.org/abs/1506.02025 http://arxiv.org/abs/1506.02025 .

HU J , SHEN L , SUN G . Squeeze-and-excitation networks‍ [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7132 - 7141 .

CHEN Y P , DAI X Y , LIU M C , et al . Dynamic convolution: Attention over convolution kernels [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 11027 - 11036 .

LI C , ZHOU A , YAO A . Omni-dimensional dynamic convolution [EB/OL ] . ( 2022-09-16 )[ 2023-08-01 ] . https://arxiv.org/abs/2209.07947 https://arxiv.org/abs/2209.07947 .

CHEN J R , KAO S H , HE H , et al . Run, don’t walk: Chasing higher FLOPS for faster neural networks [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2023 : 12021 - 12031 .

ZHANG Q L , JIANG Z Q , LU Q S , et al . Split to be slim: An overlooked redundancy in vanilla convolution [EB/OL ] . ( 2020-06-22 )[ 2023-08-01 ] . http://arxiv.org/abs/2006.12085 http://arxiv.org/abs/2006.12085 .

HAN K , WANG Y H , TIAN Q , et al . GhostNet: More features from cheap operations [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 1577 - 1586 .

王硕 , 王坚 , 王亚男 , 等 . 一种基于特征融合的恶意代码快速检测方法 [J ] . 电子学报 , 2023 , 51 ( 1 ): 57 - 66 .

WANG S , WANG J , WANG Y N , et al . A fast malicious code detection method based on feature fusion [J ] . Acta Electronica Sinica , 2023 , 51 ( 1 ): 57 - 66 . (in Chinese)

GEVORGYAN Z . SIoU loss: More powerful learning for bounding box regression [EB/OL ] . ( 2022-05-25 )[ 2023-08-01 ] . https://arxiv.org/abs/2205.12740 https://arxiv.org/abs/2205.12740 .

HE J B , ERFANI S , MA X J , et al . Alpha-IoU: A family of power intersection over union losses for bounding box regression [EB/OL ] . ( 2021-10-26 )[ 2023-08-01 ] . http://arxiv.org/abs/2110.13675 http://arxiv.org/abs/2110.13675 .

GUO D J , QIU B , LIU Y P , et al . Supernova detection based on multi-scale fusion faster RCNN [C ] // 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP) . Piscataway : IEEE , 2021 : 985 - 988 .

YU J H , JIANG Y N , WANG Z Y , et al . UnitBox: An advanced object detection network [C ] // Proceedings of the 24th ACM International Conference on Multimedia . New York : ACM , 2016 : 516 - 520 .

XU C , WANG J W , YANG W , et al . RFLA: Gaussian receptive field based label assignment for tiny object detection [C ] // Computer Vision - ECCV 2022: 17th European Conference , Part IX . New York : ACM , 2022 : 526 - 543 .

NIE G T , HUANG H . Multi-oriented object detection in aerial images with double horizontal rectangles [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 4 ): 4932 - 4944 .

HAN J M , DING J , LI J , et al . Align deep features for oriented object detection [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 5602511 .

TANG J L , LIU S B , ZHAO D X , et al . PCB-YOLO: An improved detection algorithm of PCB surface defects based on YOLOv5 [J ] . Sustainability , 2023 , 15 ( 7 ): 5963 .

CHEN B Y , DANG Z C . Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 [J ] . IEEE Access , 2023 , 11 : 95092 - 95103 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据