A Hybrid Deep Learning and Rule-Based Method for Architectural Drawing Vectorization and CAD Reconstruction
Buildings · 06.03.2026 · 16 (5) · 1043
DOI: 10.3390/buildings16051043 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 06.03.2026. Verfasst von Minqi Lin und 1 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Special Fund for Promoting High-Quality Industrial Development.
Abstract (Originalsprache)
A large number of architectural drawings have historically existed in paper form or as non-editable raster images, which makes them difficult to directly support information reuse and digital management, while manual CAD reconstruction is time-consuming and inefficient. This paper proposes a hybrid deep learning and rule-based method for architectural drawing vectorization and CAD reconstruction, which automatically converts scanned raster images into editable CAD vector files while preserving geometric structure and scale consistency. The proposed method consists of four modules: axis grid and dimension detection, text recognition and scale recovery, architectural line topology reconstruction, and CAD geometric rectification and reconstruction. The method utilizes object detection and OCR technologies to extract key semantic information from the drawings. By extracting semantic information, the method constructs a line topology structure and applies architectural drawing constraints to parameterize and normalize geometric results, thereby achieving the recognition and vectorization of raster drawings. Experimental results and engineering case studies demonstrate that the proposed method can effectively extract typical architectural elements, and generate directly editable CAD vector drawings. The method achieves favorable geometric accuracy and topological consistency in architectural drawing digitization and automatic CAD reconstruction tasks, providing a technical solution for the automatic vectorization of existing architectural drawings.
Förderung
- Shanghai Special Fund for Promoting High-Quality Industrial Development
Zitieren
APA
Lin, M., & Wang, D. (2026). A Hybrid Deep Learning and Rule-Based Method for Architectural Drawing Vectorization and CAD Reconstruction. Buildings, 16(5), 1043. https://doi.org/10.3390/buildings16051043
Vancouver
Lin M, Wang D. A Hybrid Deep Learning and Rule-Based Method for Architectural Drawing Vectorization and CAD Reconstruction. Buildings. 2026;16(5):1043. doi:10.3390/buildings16051043
BibTeX
@article{Lin2026,
author = {Lin, Minqi and Wang, Dejiang},
title = {A Hybrid Deep Learning and Rule-Based Method for Architectural Drawing Vectorization and CAD Reconstruction},
journal = {Buildings},
year = {2026},
volume = {16},
number = {5},
pages = {1043},
doi = {10.3390/buildings16051043}
}
EUVIMED