Ensemble of CNN classifiers using Choquet Fuzzy Integral Technique for PCB Defect Classification

被引:0
作者
Purahong, Boonchana [1 ]
Krungseanmuang, Woranidtha [2 ]
Tenghongsakul, Kasi [3 ]
Archevapanich, Tuanjai [4 ]
Khunthawiwone, Parkpoom [4 ]
Satayarak, Nitjaree [1 ]
Lasakul, Attasit [1 ]
机构
[1] King Mongkuts Inst Technol Ladkrabang, Sch Engn, Dept Comp Engn, Bangkok, Thailand
[2] King Mongkuts Inst Technol Ladkrabang, Sch Engn, Dept Robot & Computat Intelligent Syst, Bangkok, Thailand
[3] King Mongkuts Inst Technol Ladkrabang, Sch Engn, Dept Elect Engn, Bangkok, Thailand
[4] Rajamagala Univ Technol Suvarnabhumi, Fac Engn & Architecture, Dept Elect & Commun Engn, Nonthaburi, Thailand
来源
2024 6TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND THE INTERNET, ICCCI 2024 | 2024年
关键词
choquet integral; deep learning; ensemble method; defect detection; PCB images;
D O I
10.1109/ICCCI62159.2024.10674180
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper presents a novel method for detecting defects in printed circuit boards (PCBs) using an ensemble of classifiers based on the Choquet fuzzy integral. Our approach employs convolutional neural network (CNN) models, specifically ResNet152, VGG19, and InceptionV3 as base classifiers to identify six types of PCB defects: spurs, mouse bites, short circuits, open circuits, spurious copper, and pinholes. Given the critical role of PCBs in ensuring electronic equipment reliability, effective defect detection methods like ours are essential. We employ pre-trained CNN models for feature extraction and classification of PCB defects. Following this, we combine the prediction scores using the Choquet fuzzy integral to derive more accurate final labels, exceeding the accuracy of standalone models. Our approach is tested on PCB images obtained from public repositories, captured using a linear scan CCD.The evaluation results demonstrate average precision, recall, F-score, and accuracy of 93.0%, 95.2%, 95.1%, and 95.1%, respectively.
引用
收藏
页码:43 / 48
页数:6
相关论文
共 17 条
  • [1] Abadi Martin, 2016, Proceedings of OSDI '16: 12th USENIX Symposium on Operating Systems Design and Implementation. OSDI '16, P265
  • [2] Anitha DB, 2017, 2017 2ND IEEE INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), P39, DOI 10.1109/WiSPNET.2017.8299715
  • [3] Bisong E., 2019, BUILDING MACHINE LEA, P59, DOI DOI 10.1007/978-1-4842-4470-8
  • [4] A Light-Weighted CNN Model for Wafer Structural Defect Detection
    Chen, Xiaoyan
    Chen, Jianyong
    Han, Xiaoguang
    Zhao, Chundong
    Zhang, Dongyang
    Zhu, Kuifeng
    Su, Yanjie
    [J]. IEEE ACCESS, 2020, 8 : 24006 - 24018
  • [5] Chollet F., 2015, Keras
  • [6] Druckman J., 2024, PREPRINT, DOI [DOI 10.1214/20-BA1223, 10.31234/osf.io/h9j2d, DOI 10.31234/OSF.IO/H9J2D]
  • [7] Identity Mappings in Deep Residual Networks
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 : 630 - 645
  • [8] Detection of PCB Surface Defects With Improved Faster-RCNN and Feature Pyramid Network
    Hu, Bing
    Wang, Jianhui
    [J]. IEEE ACCESS, 2020, 8 : 108335 - 108345
  • [9] Printed Circuit Board Defect Detection Using Deep Learning via A Skip-Connected Convolutional Autoencoder
    Kim, Jungsuk
    Ko, Jungbeom
    Choi, Hojong
    Kim, Hyunchul
    [J]. SENSORS, 2021, 21 (15)
  • [10] ImageNet Classification with Deep Convolutional Neural Networks
    Krizhevsky, Alex
    Sutskever, Ilya
    Hinton, Geoffrey E.
    [J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90