Nwe, T. L., Singh Pahwa, R., Chang, R., Min, O. Z., Jie, W., Li, Y., Lin, D., Prasad, S., & Dong, S. (2022). On the Use of Component Structural Characteristics for Voxel Segmentation in Semicon 3D Images. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9747623
Detecting defects buried inside chips is critical for failure analy sis in semiconductor manufacturing. In this paper, we perform 3D voxel segmentation on 2.5D semicon chips to locate and identify defects that may be present in them. We integrate tree based En semble method with the Cascaded Anisotropic Convolutional Neural Networks to employ component structural characteristics of semi con 3D object in voxel segmentation process. We fabricate custom 2.5D chips purposely creating defective regions by using a specific fabrication and assembling process. Thereafter, use commercial 3D XRM tools for 3D imaging of these chips. We perform accurate 3D Object localization for each 3D x-ray scan by using a slice and fuse approach. Then, we perform voxel segmentation on logic die (in tegral component of semicon chip) to detect Cu-pillar, solder, and void regions (if any). The results show that we achieve state-of-the art voxel segmentation dice scores for all three sub-components.
There was no specific funding for the research done