PERFORMANCE ANALYSIS OF ARTIFICIAL INTELLIGENCE TOOLS IN DIGITIZATION OF LOST CULTURAL HERITAGE: SARAY-I AMIRE

Authors : Süleyman Aykutalp Özkuyumcu, Ayşe Kalaycı Önaç

Pages : 12-24

Doi:10.32328/turkjforsci.1676049

View : 43 | Download : 63

Publication Date : 2025-04-30

Article Type : Research Paper

Abstract :The digitization of cultural heritage plays a critical role in the preservation of historical artifacts and their transmission to future generations. This study focuses on the digital reconstruction of the Saray-ı Amire in Manisa, a lost architectural structure from the Ottoman period, and evaluates the performance of artificial intelligence (AI) tools throughout this process. Traditional modeling techniques are compared with AI-based algorithms in terms of accuracy, speed, and level of detail. Data derived from archival documents, historical maps, engravings, and analogous structures were utilized to assess the accuracy of AI-generated models using metrics such as the Structural Similarity Index (SSIM) and Root Mean Square Error (RMSE). The findings reveal that while AI tools enable rapid modeling workflows, they present certain limitations in accurately capturing architectural details. The study advocates for the adoption of hybrid methodologies in the digitization of cultural heritage and discusses both ethical and technical issues involved in digital restitution processes. Ultimately, while Prome AI was effective in generating visual textures, Fabrie AI produced more precise and analytical results, yielding geometrically detailed reconstructions. However, both tools demonstrated limitations in preserving historical accuracy and faithfully reflecting architectural intricacies. Thus, alongside the efficiency and speed offered by AI technologies, the study emphasizes the continued importance of human intervention through hybrid approaches.
Keywords : Kayıp Kültürel Miras, Yapay Zeka, Mimari Görselleştirme, Saray-ı Amire