Optics and Precision Engineering, Volume. 32, Issue 5, 740(2024)

Multispectral image fusion method for surface defect detection of IC devices

Yaohua DENG and Zhihai HUANG*
Author Affiliations
  • College of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou510006, China
  • show less

    To address the issue of low defect detection accuracy in IC devices due to insufficient contrast under either visible light or infrared conditions alone, this paper introduces a multi-spectral fusion approach. Initially, to overcome scale inconsistency and contrast inversion challenges during IC device image registration, we enhance the ORB (Oriented FAST and Rotated BRIEF) algorithm with a Laplacian pyramid and feature descriptor recombination strategy. Following image registration, we propose the NSST_VP image fusion method, which processes the infrared and visible images' low and high frequency subbands through Non-Subsample Shearlet Transform (NSST). For fusion, the low frequency subband uses a visual significance map (VSM) weighted rule, and the high frequency subband employs a PA-Pulse Coupled Neural Network (PA-PCNN) decision rule, with the final image produced by reversing the NSST. The fused image is then analyzed using the YOLOv8s model. Experimental findings reveal an 87.8% average accuracy with the improved ORB registration, marking a 62% enhancement over the standard ORB. The NSST_VP fusion algorithm significantly boosts both subjective and objective metrics, achieving an mAP of 83.15%-surpassing single light mode detections by 22.97% and 28.31%, and outperforming Dual-Tree Complex Wavelet, Non-Subsampled Contourlet, and Curvelet Transform fusion methods by 13.14%, 15.01%, and 20.35%, respectively.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Yaohua DENG, Zhihai HUANG. Multispectral image fusion method for surface defect detection of IC devices[J]. Optics and Precision Engineering, 2024, 32(5): 740

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Oct. 5, 2023

    Accepted: --

    Published Online: Apr. 2, 2024

    The Author Email: HUANG Zhihai (2112101013@mail2.gdut.edu.cn)

    DOI:10.37188/OPE.20243205.0740

    Topics