Color Extraction and Design Application of Yao Embroidery Based on K-means Algorithm

To promote the digital preservation and transmission of traditional cultural elements, this study focuses on Yao embroidery as a case study, combining digital technologies and algorithms to extract and analyze its color characteristics. These extracted color features were applied to the design of virtual character clothing. First, a bilateral filtering algorithm was used to preprocess the images of Yao embroidery, reducing noise while preserving intricate details. Subsequently, Euclidean distance was calculated in the Lab color space, and the OSTU adaptive binarization method was employed to separate the image from its background. Additionally, K-means clustering was applied multiple times to the color data, and the optimal result was achieved when the number of clusters was set to eight. Through this process, eight major colors of Yao embroidery were extracted. Based on these extracted colors, 3D point cloud analysis was conducted to study the three-dimensional spatial distribution of color points, and a color combination model based on hue, brightness, and saturation was constructed. The results revealed that the color composition of Yao embroidery predominantly consists of high-saturation colors, with strong color contrasts and distinct ethnic characteristics. Ultimately, this study demonstrated the applicability of integrating the color model and design patterns of Yao embroidery into virtual character clothing design, showcasing the potential for incorporating traditional embroidery into digital design. This contributes to the preservation and promotion of intangible cultural heritage and serves as a valuable reference for further research on the color systems of traditional ethnic costumes.