Management of Digital Sculpture Archives Using Ai
Bibliographic Data
| ID | 22196239 |
|---|---|
| Authors | Deepak Bhanot, Sarbeswar Hota, Richa Srivastava (0000-0002-7273-6047), T K Ramesh (0000-0002-6259-5172), T Ramesh T Ramesh, Amritpal Sidhu, Sagufta Parveen |
| Year | 2025 |
| Volume | 6 |
| Issue | 2s |
| Publication date | 2025-12-16 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ShodhKosh: Journal of Visual and Performing Arts (JOURNAL) |
| Journal identifiers | ISSN: 2582-7472 • E-ISSN: 2582-7472 |
| Publisher | Granthaalayah Publications and Printers (PUBLISHER • IN) |
| DOI | 10.29121/shodhkosh.v6.i2s.2025.6716 |
| OpenAlex | W4417426210 |
| Language | EN |
| References cited | 10 |
The digital management of sculptures archives has become a burning issue in the digital age in the preservation and distribution of cultural heritage. The conventional archival practices have failed in the context of the growing complexity, size, and multimodality of digital sculptures which use complex 3D geometries, textures, and metadata. The study offers an AI-based system of intelligent management and classification of digital sculpture collections and their retrieval. The suggested system will combine computer vision, deep learning, and natural language processing (NLP) and will automatize object recognition, semantic tagging, and similarity-based retrieval processes. The analysis of structural features is performed with the help of three-dimensional convolutional neural networks (3D-CNNs), and contextual metadata is derived by transformer-based models, using descriptive annotations. In addition, clustering algorithms, such as K-means and DBSCAN help to classify sculptures according to geometrical and stylistic characteristics. Accuracy, retrieval time, mean average precision are used to assess performance of the system, which is high and it can be scaled and robust to work with varied datasets. Using explainable AI methods, the model increases the transparency of classification decisions, which is why it is applicable to academic and museum usage. In addition to simplifying the administration of digital archives, such a solution will enhance accessibility, maintainability, and cross-cultural interpretation of cultural heritage, which will form the basis of future AI-based curation and cultural informatics systems
Convolutional neural network · Cultural heritage · Digital Preservation · Metadata · Ontology · Sculpture · 3D Surveying and Cultural Heritage · Aesthetic Perception and Analysis · Image Processing and 3D Reconstruction
| Citation velocity | historical |
|---|---|
| Highly cited | No |