Kengo Katayama

Papers

Total Citations

H-Index

About

Kengo Katayama is a researcher at the forefront of intelligent manufacturing and autonomous systems, with a focus on bridging computer vision and robotics for industrial applications. His work centers on integrating fuzzy inference systems with deep learning, particularly Convolutional Neural Networks (CNNs), to enhance robot vision and image recognition in manufacturing environments. Katayama’s most cited paper, "Design of a Fuzzy Inference Based Robot Vision for CNN Training Image Acquisition" (2021, 15 citations), addresses a critical bottleneck in Industry 4.0: the need for efficient, automated acquisition of training images for CNN-based inspection and testing processes. He has also contributed to emergency communications, co-authoring "Real World Emergency Scenario Using MANET in Indoor Environment" (2015, 8 citations), which explores low-cost ad hoc networks for disaster recovery. More recently, his work on microconvex recognition (2022) advances precision manufacturing. Katayama’s research demonstrates a practical, systems-level approach to deploying AI in real-world industrial settings, making him a notable figure in applied robotics and intelligent automation.