• Optoelectronic Technology
  • Vol. 41, Issue 3, 203 (2021)
Guohua FAN
Author Affiliations
  • The 55th Research Institute of China Electronic Technology Group Corporation, Nanjing 210016, CHN
  • show less
    DOI: 10.19453/j.cnki.1005-488x.2021.03.008 Cite this Article
    Guohua FAN. Arbitrary⁃oriented PCB Defect Detection via Rotation Proposals[J]. Optoelectronic Technology, 2021, 41(3): 203 Copy Citation Text show less

    Abstract

    A deep learning model for detecting PCB defects based on arbitrary-oriented object detection was proposed, which could simplify the whole process by avoiding image registration and image pre-processing. This model had two new components, including a Rotation Region Proposal Network (RRPN) and a Rotation Region-of-Interest (RRoI) pooling layer. Experiment results validated the effectiveness of the proposed model by achieving 97.2% mAP on perturbated DeepPCB dataset.
    Guohua FAN. Arbitrary⁃oriented PCB Defect Detection via Rotation Proposals[J]. Optoelectronic Technology, 2021, 41(3): 203
    Download Citation