Wafer Surface Defect Detection Based on Feature Enhancement and Predicted Box Aggregation

被引:1
作者
Zheng, Jiebing [1 ,2 ]
Dang, Jiangtao [3 ]
Zhang, Tao [2 ]
机构
[1] Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China
[2] Changshu Inst Technol, Sch Comp Sci & Engn, Suzhou 215500, Peoples R China
[3] ENGITIST CORP, Suzhou 215533, Peoples R China
基金
中国国家自然科学基金;
关键词
defect detection; feature enhancement; dynamic convolution; predicted box aggregation; Faster RCNN;
D O I
10.3390/electronics12010076
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
For wafer surface defect detection, a new method based on improved Faster RCNN is proposed here to solve the problems of missing detection due to small objects and multiple boxes detection due to discontinuous objects. First, focusing on the problem of small objects missing detection, a feature enhancement module (FEM) based on dynamic convolution is proposed to extract high-frequency image features, enrich the semantic information of shallow feature maps, and improve detection performance for small-scale defects. Second, for the multiple boxes detection caused by discontinuous objects, a predicted box aggregation method is proposed to aggregate redundant predicted boxes and fine-tune real predicted boxes to further improve positioning accuracy. Experimental results show that the mean average precision of the proposed method, when validated on a self-developed dataset, reached 87.5%, and the detection speed was 0.26 s per image. The proposed method has a certain engineering application value.
引用
收藏
页数:14
相关论文
共 28 条
  • [1] A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition
    Batool, Uzma
    Shapiai, Mohd Ibrahim
    Tahir, Muhammad
    Ismail, Zool Hilmi
    Zakaria, Noor Jannah
    Elfakharany, Ahmed
    [J]. IEEE ACCESS, 2021, 9 : 116572 - 116593
  • [2] Dynamic Convolution: Attention over Convolution Kernels
    Chen, Yinpeng
    Dai, Xiyang
    Liu, Mengchen
    Chen, Dongdong
    Yuan, Lu
    Liu, Zicheng
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, : 11027 - 11036
  • [3] Machine Learning-Based Detection Method for Wafer Test Induced Defects
    Cheng, Ken Chau-Cheung
    Chen, Leon Li-Yang
    Li, Ji-Wei
    Li, Katherine Shu-Min
    Tsai, Nova Cheng-Yen
    Wang, Sying-Jyan
    Huang, Andrew Yi-Ann
    Chou, Leon
    Lee, Chen-Shiun
    Chen, Jwu E.
    Liang, Hsing-Chung
    Hsu, Chun-Lung
    [J]. IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2021, 34 (02) : 161 - 167
  • [4] Deep open-set recognition for silicon wafer production monitoring
    Frittoli, Luca
    Carrera, Diego
    Rossi, Beatrice
    Fragneto, Pasqualina
    Boracchi, Giacomo
    [J]. PATTERN RECOGNITION, 2022, 124
  • [5] Fast R-CNN
    Girshick, Ross
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 1440 - 1448
  • [6] Optimal Feature Selection for Defect Classification in Semiconductor Wafers
    Gomez-Sirvent, Jose L.
    de la Rosa, Francisco Lopez
    Sanchez-Reolid, Roberto
    Fernandez-Caballero, Antonio
    Morales, Rafael
    [J]. IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2022, 35 (02) : 324 - 331
  • [7] Locally Adaptive Statistical Background Modeling With Deep Learning-Based False Positive Rejection for Defect Detection in Semiconductor Units
    Haddad, Bashar M.
    Dodge, Samuel F.
    Karam, Lina J.
    Patel, Nital S.
    Braun, Martin W.
    [J]. IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2020, 33 (03) : 357 - 372
  • [8] Full-Wafer Voltage Contrast Inspection for Detection of BEOL Defects
    Hafer, Richard F.
    Patterson, Oliver D.
    Hahn, Roland
    Xiao, Hong
    [J]. IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2015, 28 (04) : 461 - 468
  • [9] Polycrystalline silicon wafer defect segmentation based on deep convolutional neural networks
    Han, Hui
    Gao, Chenqiang
    Zhao, Yue
    Liao, Shisha
    Tang, Lin
    Li, Xindou
    [J]. PATTERN RECOGNITION LETTERS, 2020, 130 : 234 - 241
  • [10] Deep Residual Learning for Image Recognition
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778