Deep learning-based image compression for enhanced hyperspectral processing in the protection of stone cultural relics

Compared to the artificial identification of deterioration modes in stone cultural heritage, machine identification is more objective, detailed, accurate, timely, and cost-effective. Hyperspectral data can expand the information dimension and improve machine recognition capabilities. However, this augmentation of information introduces challenges in recognition efficiency, storage, and transmission. To address these challenges, this paper presents a deep learning radial basis function (RBF) compression algorithm, aimed at enhancing the efficacy of hyper- spectral image analysis. The experimental results show that the identification model's F1-score remained around 0.95, with an average improvement in identification accuracy of 1.4%. Overall identification efficiency was enhanced by 13.8%, the identification model's training time was reduced by an average of 4.7%, and the identification time was reduced by an average of 9.1%. It provides a new scheme based on hyperspectral for nondestructive testing of stone cultural relics. And provides the corresponding business support for the relevant units.