Bernard Shiffman
Papers
1
Total Citations
27
H-Index
1
About
Bernard Shiffman’s research centers on geometric and algebraic methods in computer vision, robotics, and sensor calibration, with a particular emphasis on solving fundamental transformation problems. His major contributions include pioneering work on the AX = XB sensor calibration problem, which is critical for image-guided therapy systems and robotic surgery. By leveraging Euclidean-group invariants, Shiffman developed a rigorous framework for solving this calibration challenge when sensor correspondence is unknown—a problem that had long hindered accurate registration in medical robotics. His 2013 paper on this topic has garnered 27 citations, reflecting its practical impact on surgical navigation and automation. Beyond this, Shiffman’s work bridges abstract algebraic geometry and real-world engineering, offering elegant solutions to problems in multi-sensor fusion and 3D reconstruction. His achievements demonstrate a rare ability to translate deep mathematical theory into deployable algorithms, making him a key figure in the intersection of geometry and applied robotics. For students and researchers, Shiffman’s research exemplifies how foundational invariants can unlock robust, real-time performance in critical medical and industrial systems.
Research Focus
Key Achievements
Top Papers
- 1