Multi-view clustering hierarchical block feature matching algorithm for ancient cultural architecture
Open Computer Science · 23.01.2026 · 16 (1)
DOI: 10.1515/comp-2025-0063 ↗Kurz gefasst
Fachartikel in der Zeitschrift Open Computer Science, online erschienen am 10.07.2026. Verfasst von Xiaowei Xu und 1 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With the acceleration of urbanization, the protection and restoration of ancient cultural buildings have become more important. To enhance the efficiency and accuracy of digital protection of ancient buildings, this study proposes a multi-view clustering, layered, and block-based feature matching algorithm for ancient cultural buildings. This algorithm first addresses the issues of high computational complexity and easy loss of important feature information in high-dimensional multi-view information by using non-negative matrix factorization and adaptive fusion view structure. Then, a hierarchical block feature matching model based on the scale invariant feature transformation algorithm is constructed to optimize the robustness of the algorithm. The experiment showed that when the iteration number was 200, the normalized information value of the multi-view clustering algorithm in the ORL dataset was 0.924, and the loss was 0.040. For the feature matching algorithm, its matching accuracy was 97.67 %, and the matching time was 0.96 s. This indicated that the matching efficiency and accuracy of the developed algorithm were superior to those of current advanced algorithms. This study offers innovative technological solutions for protecting and restoring cultural heritage by leveraging advanced computer vision technology to safeguard ancient cultural buildings.
Zitieren
APA
Xu, X., & Chen, P. (2026). Multi-view clustering hierarchical block feature matching algorithm for ancient cultural architecture. Open Computer Science, 16(1). https://doi.org/10.1515/comp-2025-0063
Vancouver
Xu X, Chen P. Multi-view clustering hierarchical block feature matching algorithm for ancient cultural architecture. Open Computer Science. 2026;16(1). doi:10.1515/comp-2025-0063
BibTeX
@article{Xu2026,
author = {Xu, Xiaowei and Chen, Penghua},
title = {Multi-view clustering hierarchical block feature matching algorithm for ancient cultural architecture},
journal = {Open Computer Science},
year = {2026},
volume = {16},
number = {1},
doi = {10.1515/comp-2025-0063}
}
EUVIMED