Published Paper Details:

Counterfeit detection in art and antiques is a persistent issue that undermines the value of cultural heritage and economic markets globally. Traditional methods of art authentication, while effective, rely heavily on expert evaluations, which can be time-consuming, costly, and prone to human error. This research aims to develop an innovative solution using Artificial Intelligence (AI) to automate and enhance the process of counterfeit detection. The proposed system integrates advanced machine learning techniques, such as Convolution Neural Networks (CNNs) for image-based analysis, which can detect subtle inconsistencies in brushstrokes, patterns, and textures, which are typically difficult for the human eye to discern. In addition to visual analysis, hyper spectral imaging (HSI) will be utilized to examine the materials and hidden layers of artworks, identifying anachronistic pigments, modern binders, or mismatched materials, further improving the accuracy of detection. Provenance validation, an integral aspect of art authentication, will be achieved using blockchain technology to ensure secure, immutable records of an artwork's history. By merging these AI approaches, the system offers a comprehensive solution that is both scalable and cost-effective for art galleries, auction houses, and collectors. This research has the potential to significantly reduce the occurrence of fraud in the art market, improve transparency, and preserve the integrity of cultural artifacts for future generations.