Tom Gregorich

Carl Zeiss (United States)

Papers

1

Total Citations

18

H-Index

1

About

Tom Gregorich is a researcher at the forefront of applying deep learning to non-destructive evaluation, with a particular focus on automated analysis of 3D X-ray imagery. His work bridges computer vision and security applications, most notably through his highly cited 2021 paper on automated attribute measurements of buried package features. In this study, Gregorich demonstrates how state-of-the-art deep learning models can be trained to detect and segment concealed structures in volumetric X-ray scans—a task critical for security screening and industrial inspection. By adapting techniques from robotics and medical imaging, he has shown that neural networks can reliably identify buried objects and measure their geometric attributes with minimal human intervention. His contributions are helping to move automated threat detection from research labs into practical deployment, with his work already accumulating 18 citations and growing. Gregorich’s research stands out for its direct applicability to real-world security challenges, making him a notable voice in the intersection of deep learning, 3D imaging, and safety-critical systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
18
Total Citations
18
Avg Citations/Paper
🏆 Most Cited Paper
Automated Attribute Measurements of Buried Package Features in 3D X-ray Images using Deep Learning
18 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 12
🏛 Institutions: Carl Zeiss (United States)

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago