Elevating wafer defect inspection with denoising diffusion probabilistic model
College
Gokongwei College of Engineering
Department/Unit
Center for Engineering and Sustainable Development Research
Document Type
Article
Source Title
Mathematics
Volume
12
Publication Date
2024
Abstract
Integrated circuits (ICs) are critical components in the semiconductor industry, and precise wafer defect inspection is essential for maintaining product quality and yield. This study addresses the challenge of insufficient sample patterns in wafer defect datasets by using the denoising diffusion probabilistic model (DDPM) to produce generated defects that elevate the performance of wafer defect inspection. The quality of the generated defects was evaluated using the Fréchet Inception Distance (FID) score, which was then synthesized with real defect-free backgrounds to create an augmented defect dataset. Experimental results demonstrated that the augmented defect dataset significantly boosted performance, achieving 98.7% accuracy for YOLOv8-cls, 95.8% box mAP for YOLOv8-det, and 95.7% mask mAP for YOLOv8-seg. These results indicate that the generated defects produced by the DDPM can effectively enrich wafer defect datasets and enhance wafer defect inspection performance in real-world applications.
html
Recommended Citation
Wu, P., Thi, H. P., Chou, Y., Mayol, A., Lai, Y., Kang, C., Chan, Y., Lin, S., & Chen, S. (2024). Elevating wafer defect inspection with denoising diffusion probabilistic model. Mathematics, 12 Retrieved from https://animorepository.dlsu.edu.ph/faculty_research/14409
Disciplines
Manufacturing
Keywords
Integrated circuits—Defects; Semiconductor wafers—Defects
Upload File
wf_no