Integrating Visual and X-Ray Machine Learning Features in the Study of Paintings by Goya

Researchers have developed a new multimodal machine learning framework designed to improve the authentication of Francisco Goya's paintings by integrating features extracted from both visual and X-ray images. This approach applies consistent feature extraction techniques across these two imaging modalities to address the complexities posed by Goya's varied artistic styles and the historical prevalence of forgeries. The primary goal of this framework is to enhance the accuracy and reliability of art authentication processes. By leveraging machine learning, the method aims to provide a more objective and data-driven assessment compared to traditional expert evaluations. The proposed framework has been positively received as a promising tool in the field of art analysis. This development aligns with ongoing efforts to apply advanced computational techniques to cultural heritage preservation and art history research. Overall, the integration of visual and X-ray features represents a significant step toward more robust authentication methodologies for artworks with complex provenance.