Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

Image Processing and Deep Learning-based Defect Detection Theory for Sapphire Epi-Wafer in Green LED Manufacturing

  • Suk Ju Ko (Department of Electronics Engineering, Myongji University) ;
  • Ji Woo Kim (Department of Electronics Engineering, Myongji University) ;
  • Ji Su Woo (Department of Industrial and Management Engineering, Myongji University) ;
  • Sang Jeen Hong (Department of Semiconductor Engineering, Myongji University ) ;
  • Garam Kim (Department of Electronics Engineering, Myongji University)
  • Received : 2023.06.02
  • Accepted : 2023.06.21
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, there has been an increased demand for light-emitting diode (LED) due to the growing emphasis on environmental protection. However, the use of GaN-based sapphire in LED manufacturing leads to the generation of defects, such as dislocations caused by lattice mismatch, which ultimately reduces the luminous efficiency of LEDs. Moreover, most inspections for LED semiconductors focus on evaluating the luminous efficiency after packaging. To address these challenges, this paper aims to detect defects at the wafer stage, which could potentially improve the manufacturing process and reduce costs. To achieve this, image processing and deep learning-based defect detection techniques for Sapphire Epi-Wafer used in Green LED manufacturing were developed and compared. Through performance evaluation of each algorithm, it was found that the deep learning approach outperformed the image processing approach in terms of detection accuracy and efficiency.

Keywords

Acknowledgement

This study was conducted with the support through the Korea Institute for Advancement of Technology (G02P1880 0005501). We would like to express our gratitude to Nexus1 for the providing research topic, mentoring, and assistance.

References

  1. H.K. Cho, J.Y. Lee, G.M. Yang, C.S. Kim, "Formation mechanism of V defects in the InGaN/GaN multiple quantum wells grown on GaN layers with low threading dislocation density," Applied Physics Letters., Vol. 79, No. 2, pp. 215-217, 2001.  https://doi.org/10.1063/1.1384906
  2. R. Colby, Z. Liang, I.H. Wildeson, D.A. Ewoldt, T.D. Sands, R.E. Garcia, E.A. Stach, "Dislocation filtering in GaN nanostructures," Nano Letter., Vol. 10, No. 5, pp. 1568-1573, 2010.  https://doi.org/10.1021/nl9037455
  3. William A. Melton, Jacques I, Pankove, "GaN growth on sapphire," Journal Of Crystal Growth., Vol. 178, No. 1, p. 168, 1997. 
  4. B. Lee, "Optical properties of InGaN/GaN active layer based blue-green light-emitting diodes," Master's thesis, Graduate Schoo of Kangwon National University l, 2020. 
  5. S.R. Kim, "Non-Referential Defect Detection based on Image Patch Similarity of Semiconductor Scanning Electron Microscope Image," Master's thesis, Graduate School of Hanyang University, 2017. p. 7 
  6. Tamas Czimmermann, Gastone Ciuti, Mario Milazzo, Marcello Chiurazzi, Stefano Roccella, Calogero Maria Oddo, Paolo Dario, "Visual-Based Defect Detection and Classification Approaches for Industrial Applications-A SURVEY," Sensors., Vol. 20, No. 5, p.1495, 2020. 
  7. Yingjie Yin, De Xu, Zhengtao Zhang, Mingran Bai, Feng Zhang, Xian Tao, Xingang Wang, "Surface Defect Detection on Optical Devices Based on Microscopic Dark-Field Scattering Imaging," Strojniski Vestnik., Vol. 61, No. 1, pp. 24-32, 2015.  https://doi.org/10.5545/sv-jme.2014.1644
  8. Baik Seung Yeb. "Development of Automatic Precision Inspection System for Defect Detection of Photovoltaic Wafer," Journal of the Korean Society of Manufacturing Technology Engineers., Vol. 20, No. 5, pp.666-672, 2011. 
  9. Y.J Park, "Development of Bolt Tap Shape Inspection System Using Computer Vision Technology," Journal of Digital Convergence., Vol. 16, No. 3, pp. 303-309, 2018. 
  10. N.H Kim, H.J Lee, H.J Jeong, J.G Lee, "Automatic detection system for surface defects of home appliances based on machine vision," Smart Media Journal., Vol. 11, No. 9, pp. 47-55, 2022.  https://doi.org/10.30693/SMJ.2022.11.9.47
  11. S.H Jeong, S.H Yoo, D.H Joung, H.B Lee, "Development of Vision Inspection system for detecting surface defects of shaft," Proceedings of the Autumn Conference and Exhibition of the Korea Society of Automotive Engineers., pp. 2196-2200, 2012. 
  12. HE, Kaiming, et al. "Deep residual learning for image recognition," Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 770-778, 2016.