基于BP神经网络的春夏女装流行色预测  

Forecast of women′s spring/summer fashion color based on BP neural networks

作　　者：狄宏静[1] 刘冬云[1] 吴志明[1] 

机构地区：[1]江南大学纺织服装学院,江苏无锡214122

出　　处：《纺织学报》2011年第7期111-116,126,共7页Journal of Textile Research

基　　金：江苏省教育厅2009年度高校哲学社会科学基金指导项目(09SJD760011);教育部人文社会科学规划项目(09YJA760015)

摘　　要：应用科学的CIELab色度测量方法,对国内权威机构发布的2001—2011年度春夏女装流行色色卡进行量化,色卡量化样本分项统计和图表分析结果显示,春夏女装流行色属性存在不变、渐变与突变的三重特征。在此基础上,进行2011年春夏流行色色相、色调频数以及红色调L*、a*、b*对应的最小和最大值估计下色调分布的BP神经网络预测与检验以及2012年再预测。结果表明,2011年各项预测结果与实际流行趋势发布基本吻合,表明该方法能科学、全面、连续地预测流行色,丰富流行色预测理论。Women′s spring/summer（S/S） fashion color cards released by the domestic authority from 2001 to 2011 were quantified in this paper,and a scientific method of CIELab color measurement is applied.The partial statistics and chart analysis of color card quantitative sample show that there are triple features of women′s S/S fashion color,i.e.,constant,gradation and mutation.Basis on this study,fashion color hue and tone number,as well as the tone distribution of red color corresponding to the min and max value of L＊,a＊ and b＊,are forecasted and estimated in 2011 and re-forecasted in 2012 by BP neural networks.The forecast results in 2011 are basically coincident with the actual fashion trends release,which shows that this is a scientific,comprehensive,continuous fashion color forecast method which has enriched the fashion color forecast theories.

关 键 词：流行色 Lab色彩空间 量化分析 BP神经网络 预测 

分 类 号：TS941.13[轻工技术与工程—服装设计与工程]