摘要
为客观表述民族服饰的色彩构成,对选取的民族服饰主色进行了示范性度量和可视化表达。文章将选取的450幅图像色彩统一转换至HSV空间,利用K-均值聚类法分别对各民族服饰色彩进行聚类,提取各民族服饰的主色。依据色彩距离度量准则,重新优化主色的分布比例,并统计得出色相、饱和度及明度分布形态。实验结果表明,该方法能够有效地提取民族服饰主色,以可视化的方式表达出色彩特征值的分布情况。基于图像分析技术的色彩量化研究,有助于客观、准确地展示服饰色彩构成形态,为系统研究少数民族服饰色彩形成机制提供了可靠的测量方法。
In order to objectively describe the color composition of ethnic costumes, the main colors of ethnic costume samples were measured and visually expressed. Concretely, the colors of 450 costume images were uniformly converted to HSV color space. Then the K -means clustering method was utilized to cluster the colors and extract the main colors of ethnic costumes. Finally, according to the color distance metrics, the distribution ratio of each main color was re-optimized, and the color hue, saturation and brightness distribution pattern was gained. Results showed that the proposed method can effectively extract the main colors of ethnic costumes, and visualize the distribution of color characteristic values. Color quantitative research based on the image analysis technology contributes to accurately and objectively displaying the color composition, and provides a reliable measurement method for the color formation mechanism research of ethnic costumes.
作者
徐平华
冒海琳
张玉杰
顾冰菲
张艳清
XU Pinghua;MAO Hailin;ZHANG Yujie;GU Bingfei;ZHANG Yanqing(School of Fashion Design & Engineering,Zhejiang Sci-Tech University,Hangzhou 310018,China;Clothing Engineering Research Center of Zhejiang Province,Zhejiang Sci-Tech University,Hangzhou 310018,China;Jiangsu Yihai Clothing Co.,Ltd.,Nantong 226007,China)
出处
《丝绸》
CAS
CSCD
北大核心
2019年第3期24-29,共6页
Journal of Silk
基金
国家自然科学基金项目(61702460
61702461)
浙江省教育厅科研项目(Y201738456)
浙江省服装工程技术研究中心开放基金项目(2018FZKF11)
浙江理工大学一流学科优秀博士专项(2017YBZX15)
浙江理工大学科研启动基金项目(17072067-Y)
关键词
民族服饰
色彩
量化
聚类
HSV空间
ethnic costumes
color
quantification
clustering
HSV space
