Detection and Recognition of Visual Geons Based on Specific Object-of-Interest Imaging Technology

Across domains such as visual processing, computer graphics, neuroscience, and biological sciences, geons are recognized as fundamental components of complex shapes. Their theoretical significance has been extensively acknowledged in scientific research. However, accurately identifying and extracting these structural components remains a persistent challenge. This study integrates theoretical foundations from signal processing, computer graphics, neuroscience, and biological sciences. We employ specific object-of-interest imaging and neural networks to mathematically operationalize visual geon characterization, thereby elucidating their intrinsic properties. Experiments validate the core hypothesis of geon theory, namely that geons are foundational components for the visual system to recognize complex objects. Through training, neural networks are capable of identifying distinct basic geons and, on this basis, performing target recognition in more complex scenarios. These findings provide empirical confirmation of geons' existence and their critical role in visual recognition, establishing novel computational paradigms and theoretical foundations for interdisciplinary research.