Color corrected costume color structure in Sun Wen’s Dream of the Red Chamber illustrations

This study analyzes costume color structures in Sun Wen’s illustrated Dream of the Red Chamber through a reproducible image-based workflow. Character regions were extracted from 203 digitized illustrations with character detection and the Segment Anything Model, producing 3,709 character samples. A paper-color anchoring procedure based on the Von Kries chromatic adaptation model was used to reduce cross-image background variation, after which five weighted dominant colors were extracted for each sample in CIELAB space. Uniform Manifold Approximation and Projection and Ward hierarchical clustering were used to explore palette groupings. The results show that the samples can be categorized into six recurring color scheme types, which form four higher-level color scheme clusters. The differences between the various types are primarily reflected in the degree of concentration of the dominant colors and the manner in which secondary colors are incorporated, providing a verifiable quantitative description of costume color schemes in Sun Wen’s illustrations.

Authors

Institutions

Publication Details

Journal
npj Heritage Science
Published
2026-11-14
DOI
https://doi.org/10.1038/s40494-026-03108-z
Primary Topic
Color Science and Applications
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Color corrected costume color structure in Sun Wen’s Dream of the Red Chamber illustrations

Chun Zhu, Juan Chai, Haitao Wang, Kaixuan Liu
1 links
npj Heritage Science
Color Science and Applications
article

Color corrected costume color structure in Sun Wen’s Dream of the Red Chamber illustrations

Chun Zhu, Juan Chai, Haitao Wang, Kaixuan Liu
article en

Abstract

This study analyzes costume color structures in Sun Wen’s illustrated Dream of the Red Chamber through a reproducible image-based workflow. Character regions were extracted from 203 digitized illustrations with character detection and the Segment Anything Model, producing 3,709 character samples. A paper-color anchoring procedure based on the Von Kries chromatic adaptation model was used to reduce cross-image background variation, after which five weighted dominant colors were extracted for each sample in CIELAB space. Uniform Manifold Approximation and Projection and Ward hierarchical clustering were used to explore palette groupings. The results show that the samples can be categorized into six recurring color scheme types, which form four higher-level color scheme clusters. The differences between the various types are primarily reflected in the degree of concentration of the dominant colors and the manner in which secondary colors are incorporated, providing a verifiable quantitative description of costume color schemes in Sun Wen’s illustrations.

npj Heritage Science
Shanxi University (CN), Xi'an Polytechnic University (CN)
Education Department of Shaanxi Province
Color Science and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon