Analyzes architectural color changes in historic districts, suggesting patterns of color evolution.
Urban color homogenization threatens heritage cities, yet longitudinal records of individual buildings across historical periods are rarely available, requiring quantitative methods to infer cross-period chromatic correspondences from period-representative samples. This study reframes cross-period architectural color comparison as a bipartite optimal matching problem, integrating facade semantic segmentation, perception-weighted HSV clustering, and Hungarian-algorithm matching. Applied to 153 buildings across eight historic districts of Dalian spanning four periods (1898–2014), the method reconstructed period-specific color-gene profiles and their cross-period correspondences. Results show cross-period correspondence remained stable through the early-to-mid twentieth century, declined markedly between 1905–1949 and 1950–1978, and dominant-color composition broadened after 1979. Among 12 recurring color gene units, five appeared across all four periods, concentrated in warm hues of moderate saturation, while two emerged only after 1979 in low-saturation neutrals. A “color gene map” is proposed for comparing period-specific patterns and cross-period correspondences in historic districts.
No takes yet. Share an insight, caveat, or question.
E et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: