Modelling the perception of visual design principles on façades through fuzzy sets: towards building an automated architectural data generation and labelling tool


Cekmis A.

Architectural Science Review, 2023 (AHCI) identifier

  • Publication Type: Article / Article
  • Publication Date: 2023
  • Doi Number: 10.1080/00038628.2023.2269549
  • Journal Name: Architectural Science Review
  • Journal Indexes: Arts and Humanities Citation Index (AHCI), Scopus, IBZ Online, Aerospace Database, Art Source, Avery, Communication Abstracts, Compendex, ICONDA Bibliographic, INSPEC, Metadex, Civil Engineering Abstracts
  • Keywords: Automated labelling, Data generation, Façade design, Fuzzy Logic, Parametric modelling, Visual design principles
  • Istanbul Technical University Affiliated: Yes

Abstract

Recent studies showed that deep learning techniques and image processing can identify the distinguishing design principles in architectural façades. However, predicting the strength of a principle is still a challenging task, as it requires a huge amount of annotated design variations. The difficulties in both searching such big numbers of data–and its labelling by experts–slow down the research. This paper proposes a computation approach for obtaining this type of data faster. With the help of parametric modelling and evolutionary algorithms, we could manipulate the design elements, and thereby generate different solutions. An integrated fuzzy logic decision mechanism could enable to carry human knowledge in the judging and labelling of alternatives automatically. The final synthetic data developed from real building images could be used for machine learning applications to enhance our understanding of artistic expression.