A Web-based system for rock classification leveraging RGB and hyperspectral imaging

This study introduces a novel scientific approach that integrates hyperspectral imaging and artificial intelligence to enhance rock type classification. A core contribution of this work is the development of an original segmentation algorithm capable of identifying subtle mineralogical variations in core samples. This algorithm enables the automated classification of diverse rock types with high accuracy and interpretability. The original algorithms were implemented into a user-friendly application that streamlines the image analysis process, thereby reducing dependency on expert geological interpretation. This enables rapid and reliable evaluation, even by non-specialist users. To validate the application's performance, a case study was conducted. Comparing the segmentation-based rock type classification with conventional visual inspection and Python-based scripts, confirming comparable accuracy. The findings demonstrate that the proposed system offers both scientific novelty and practical value, contributing to the advancement of non-contact, efficient, and accurate geotechnical analysis in both research and field environments.