Article: AI recognition of art sculpture styles based on seagull optimisation machine learning Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.25 pp.87 - 103 Abstract: This paper proposes an innovative solution based on the improved seagull optimisation algorithm (ISOA) for the key technical challenges of art sculpture style recognition in digital protection of cultural heritage. Through the design of quantum-chaos hybrid initialisation strategy and dynamic nonlinear parameter system, it breaks through the bottleneck of early convergence of traditional optimisation algorithms in high-dimensional feature space, and combines the 3D differential geometric feature enhancement model and multimodal data fusion technology to construct an intelligent recognition framework with deformation robustness. Experiments show that the algorithm achieves 96.5% recognition accuracy on the dataset, which is 8.2% higher than the mainstream model. It provides a new generation of technical paradigm for the protection and intelligent identification of art treasures. Inderscience Publishers - linking academia, business and industry through research

Title: AI recognition of art sculpture styles based on seagull optimisation machine learning

Authors: Fan Zhao

Addresses: Department of Plastic Arts, Zhengzhou Academy of Fine Arts, Zhengzhou 451450, China

Abstract: This paper proposes an innovative solution based on the improved seagull optimisation algorithm (ISOA) for the key technical challenges of art sculpture style recognition in digital protection of cultural heritage. Through the design of quantum-chaos hybrid initialisation strategy and dynamic nonlinear parameter system, it breaks through the bottleneck of early convergence of traditional optimisation algorithms in high-dimensional feature space, and combines the 3D differential geometric feature enhancement model and multimodal data fusion technology to construct an intelligent recognition framework with deformation robustness. Experiments show that the algorithm achieves 96.5% recognition accuracy on the dataset, which is 8.2% higher than the mainstream model. It provides a new generation of technical paradigm for the protection and intelligent identification of art treasures.

Keywords: improved seagull optimisation algorithm; ISOA; 3D differential geometric features; multimodal data fusion; digital preservation of cultural heritage.

DOI: 10.1504/IJICT.2025.147139

International Journal of Information and Communication Technology, 2025 Vol.26 No.25, pp.87 - 103

Received: 16 May 2025
Accepted: 29 May 2025
Published online: 10 Jul 2025 *

Title: AI recognition of art sculpture styles based on seagull optimisation machine learning

Keep up-to-date