Papers
2
Total Citations
12
H-Index
2
About
De Wen Soh is a researcher at the forefront of applying computer vision to critical industrial challenges, with a primary focus on aviation safety and automated inspection systems. His most impactful work centers on aircraft skin defect detection, where he has systematically advanced the field by surveying and benchmarking state-of-the-art deep learning models. Notably, his 2025 survey provides a rigorous comparison of YOLOv9 and RT-DETR, demonstrating how modern object detection architectures can automate the detection of surface defects that are currently identified through manual or visual inspections—a process vital for aviation safety. With over 12 citations across his key publications, Soh’s contributions are already shaping the transition from labor-intensive inspection methods to reliable, real-time automated systems. His work not only highlights the practical deployment of computer vision in high-stakes environments but also offers a clear roadmap for future research in defect detection. For students and researchers in applied AI, Soh’s research exemplifies how cutting-edge algorithms can solve real-world safety problems, making him a notable voice in the intersection of computer vision and aerospace engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2