
doi: 10.1145/3704803
This study advances the understanding of architectural heritage by introducing a novel analytical approach for classifying geometric decorations. Through the integration of image clustering and statistical analysis, the research establishes a robust framework for examining the development of decorative styles in Ilkhanid architecture (1256–1335 CE), renowned for its vibrant and intricate designs. Focusing on the “shamsa,” a star-shaped geometric motif symbolizing the sun and frequently represented through intersecting lines, the study employs a four-stage process: (1) collecting and processing images of decorative elements; (2) developing and applying an unsupervised clustering algorithm to identify meaningful image groups; (3) creating a comprehensive metadata inventory for each image to support analysis; and (4) interpreting the clustered groups to reveal significant patterns and stylistic insights. Analyzing over 230 images from 34 Ilkhanid buildings using hierarchical clustering produced dendrograms illustrating relationships among the image groups. The metadata inventory validated the clusters by incorporating information on region, function, materials, and geometric patterns. This process identified 12 distinct groups of geometric patterns, demonstrating a range of complexity from simple designs to intricate knot motifs, or “gereh.” Ilkhanid decorations predominantly featured materials such as tile, brick, and plaster, with cyan, brick red, azure, and white being the primary colors. The findings present a comprehensive typology of architectural decorations, surpassing prior studies by analyzing broader features.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 2 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Top 10% | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
