Automated Attribute Measurements of Buried Package Features in 3D X-ray Images using Deep Learning

Page view(s)
22
Checked on Nov 09, 2024
Automated Attribute Measurements of Buried Package Features in 3D X-ray Images using Deep Learning
Title:
Automated Attribute Measurements of Buried Package Features in 3D X-ray Images using Deep Learning
Journal Title:
2021 IEEE 71st Electronic Components and Technology Conference (ECTC)
Keywords:
Publication Date:
10 August 2021
Citation:
Pahwa, R. S., Lay Nwe, M. T., Chang, R., Min, O. Z., Jie, W., Gopalakrishnan, S., … Gregorich, T. (2021). Automated Attribute Measurements of Buried Package Features in 3D X-ray Images using Deep Learning. 2021 IEEE 71st Electronic Components and Technology Conference (ECTC). doi:10.1109/ectc32696.2021.00345
Abstract:
Deep Learning is being widely used to identify and segment various structures in 2D and 3D scans in fields such as robotics and medical imaging. We leverage this exciting technology to train state-of-the-art models for 3D object detection and segmentation for various buried structures such as Through Silicon Vias (TSVs), memory bumps, and logic bumps. We show in detail how we fabricate our wafers and generate 3D scans. Thereafter, we explain our approach in locating these different structures in 3D scans and how we further segment these structures into solders, voids, Cu-Pillars, and Cu-Pads for 3D metrology and defect identification. We compare our approach with state-of-the-art techniques and perform a thorough analysis to discuss the advantages and disadvantages of various approaches in each step.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR EDB - Deep Learning Center of Excellence (COE) for 3D-2D Metrology
Grant Reference no. : I1901E0048
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2377-5726
0569-5503
ISBN:
978-1-6654-4097-4
978-1-6654-3120-0
Files uploaded:

File Size Format Action
ectc-1.pdf 3.64 MB PDF Open