Graham Sexton

Papers

Total Citations

H-Index

About

Graham Sexton is a researcher whose work lies at the intersection of computer vision, pattern recognition, and intelligent optimization. His key contributions focus on advancing facial expression recognition systems—a critical technology for fields like medical imaging, surveillance, and human-robot interaction. In his most-cited work, Sexton introduced a novel approach using modified Local Gabor Binary Patterns (LGBP) for feature extraction, coupled with a firefly-based optimization algorithm to enhance recognition accuracy. This research, published in 2017 and garnering 16 citations, demonstrates his ability to blend bio-inspired computing with practical machine learning challenges. By refining how machines interpret subtle human emotions, Sexton’s work has implications for more intuitive human-computer interfaces and assistive technologies. His research stands out for its innovative use of metaheuristic algorithms to solve complex feature selection problems, offering a pathway to more efficient and robust recognition systems. For students and researchers exploring the frontiers of affective computing and optimization-driven machine learning, Sexton’s contributions provide a compelling example of how nature-inspired algorithms can solve real-world vision tasks.