The dataset is a self-constructed wafer surface defect dataset, with each image captured in real-time. The extraction and segmentation of wafer image have been performed, and each image represents a single individual die. The dataset primarily includes images of defect-free dies, as well as four types of defective images: particle, scratch, stain, and liquid residual. A total of 500 images are included, and the various types of defects within the images have been annotated using the Make Sense online annotation tool.

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

[1] Mengyun Li, "Wafer Surface Defect", IEEE Dataport, 2024. [Online]. Available: http://dx.doi.org/10.21227/7x9f-zt52. Accessed: Dec. 08, 2024.
@data{7x9f-zt52-24,
doi = {10.21227/7x9f-zt52},
url = {http://dx.doi.org/10.21227/7x9f-zt52},
author = {Mengyun Li },
publisher = {IEEE Dataport},
title = {Wafer Surface Defect},
year = {2024} }
TY - DATA
T1 - Wafer Surface Defect
AU - Mengyun Li
PY - 2024
PB - IEEE Dataport
UR - 10.21227/7x9f-zt52
ER -
Mengyun Li. (2024). Wafer Surface Defect. IEEE Dataport. http://dx.doi.org/10.21227/7x9f-zt52
Mengyun Li, 2024. Wafer Surface Defect. Available at: http://dx.doi.org/10.21227/7x9f-zt52.
Mengyun Li. (2024). "Wafer Surface Defect." Web.
1. Mengyun Li. Wafer Surface Defect [Internet]. IEEE Dataport; 2024. Available from : http://dx.doi.org/10.21227/7x9f-zt52
Mengyun Li. "Wafer Surface Defect." doi: 10.21227/7x9f-zt52