A qualitative feature‐based characterization of 2D architectural style

Abstract

Architectural plans are design diagrams that describe building layout where space is planned according to design requirements. Style in architecture is generally characterized as common features appearing in a particular class of building design. This research seeks to address how to recognize architectural design style from a 2D plan diagram. We explore this question in a computational encoder-analyzer (E-A) model for 2D plans, where a characterization of 2D style is based on qualitative spatial representation and information theoretic measures. In a preliminary study of a prominent architect's plans, we demonstrate the effectiveness of our approach. We conclude by discussing practical applications of automated plan recognition and classification in design support tools.

Biological first principles for design competence

“…The second issue is to apply these cognitive mechanisms as a "package" to study how they would have been useful in an evolutionary sense (Dunbar & Barrett, 2007), that is, how they provided a selective advantage. Let us take the notion of style (Jupp & Gero, 2006). The emergence of design styles would have been as useful as the emergence of different "languages" as a way to unify and demarcate social groups.…”

Automated Representation of Style by Feature Space Archetypes: Distinguishing Spatial Styles from Generative Rules

“…Another approach quantifies style by various measurements taken from the works. More general analytical techniques using information theoretic measures have been used to measure distance between individual plans [16], and to derive values for measurements such as entropy [17], morphology and topology [18] that can be used to evaluate examples of a style.These have the advantage of quantifying designs of any style as real values on the same scales, so that variations within or between styles can be measured uniformly.…”