Efficient Multi-Modal Learning for Dual-Energy X-ray Image-Based Low-Grade Copper Ore Classification

The application of efficient optical-electrical sorting technology for the automatic separation of copper mine waste rocks not only enables the recovery of valuable copper metals and promotes the resource utilization of non-ferrous mine waste, but also conserves large areas of land otherwise used for waste disposal and alleviates associated environmental issues. However, the process is challenged by the low copper content and fine dissemination of copper-bearing minerals, including copper metallic elements, and the subdued irradiation response of sulfur. To address these challenges, this study leverages dual-energy X-ray imaging and multi-modal learning, proposing a lightweight twin-tower convolutional neural network (CNN) designed to fuse high- and low-energy spectral information for the automated sorting of copper mine waste rocks. Additionally, the study integrates an emerging Kolmogorov-Arnold network as a classifier to enhance the sorting performance. To validate the efficacy of our approach, a dataset comprising 31,057 pairs of copper mine waste rock images with corresponding high and low-energy spectra was meticulously compiled. The experimental results demonstrate that the proposed lightweight method achieves competitive, if not superior, performance compared to contemporary mainstream deep learning networks, yet it requires merely 1.32 million parameters (only 6.2% of ResNet-34), thereby indicating extensive potential for practical deployment.