Loris Nanni

Papers

Total Citations

H-Index

About

Loris Nanni is a leading researcher in computer vision and pattern recognition, with a primary focus on automated defect detection and medical image analysis. His work bridges the gap between industrial inspection and biomedical imaging, developing innovative approaches for visual recognition systems. Nanni's major contributions include pioneering thermographic inspection methods for crack detection in metal parts, where he integrated robotic workcells with thermal imaging to create robust quality control systems. His 2015 paper on this topic has garnered 18 citations, establishing foundational work in non-destructive testing. More recently, Nanni has advanced medical image segmentation through deep learning ensembles, particularly for polyp detection in colonoscopy examinations. His 2021 work on Stochastic Activation Selection for polyp segmentation addresses the critical challenge of accurate lesion identification, achieving precise semantic segmentation that can improve early cancer diagnosis. This research demonstrates his ability to adapt cutting-edge deep learning techniques to pressing medical needs. Nanni's knowledge-based approaches to defect detection further showcase his interdisciplinary expertise, combining domain-specific knowledge with computational methods. His work continues to influence both industrial automation and clinical decision support systems.