Papers
7
Total Citations
76
H-Index
5
About
Richard Chang is a leading researcher at the intersection of deep learning and industrial 3D X-ray imaging, with a primary focus on automated defect detection, segmentation, and metrology for advanced semiconductor packaging. His major contributions center on developing semi-supervised deep learning approaches that enable robust, high-accuracy identification and measurement of buried structures—such as High Bandwidth Memory (HBM) components—within complex 3D voxelized data. By adapting state-of-the-art techniques from medical imaging and robotics, Chang has pioneered methods that significantly reduce the need for large labeled datasets while maintaining precise object detection and segmentation performance. His most cited works, including papers from 2021 to 2023, have collectively garnered over 70 citations, reflecting strong interest from both academia and industry in automated inspection for semiconductor manufacturing. Notably, his 2021 survey on object detection performance under different data distributions provides foundational insights for model generalization. Chang’s research directly addresses critical challenges in quality control and process optimization for next-generation electronics, making his work highly relevant for students and engineers seeking to apply deep learning to real-world industrial metrology and defect analysis.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7