David Ho Soon Wee
Papers
1
Total Citations
18
H-Index
1
About
David Ho Soon Wee is a researcher at the forefront of applying deep learning to industrial X-ray imaging, with a focus on automated non-destructive evaluation. His key research areas include 3D object detection, semantic segmentation, and the characterization of buried features in volumetric scans. His most cited work, "Automated Attribute Measurements of Buried Package Features in 3D X-ray Images using Deep Learning" (2021, 18 citations), demonstrates how state-of-the-art neural networks can be trained to identify and measure structures like through-hole vias and solder joints within complex 3D X-ray data. This contribution bridges the gap between advanced computer vision techniques—typically used in medical imaging and robotics—and practical manufacturing quality control. By enabling precise, automated attribute measurement of hidden features, his work significantly reduces the need for manual inspection and enhances reliability in electronics assembly. David’s research stands out for its direct industrial applicability, offering a scalable solution for high-throughput inspection. His achievements highlight the growing impact of deep learning in transforming traditional engineering fields, making him a notable figure in applied machine learning for materials characterization.
Research Focus
Key Achievements
Top Papers
- 1