基于特征参数的青年女性乳房形态分析  

Research on breast shape of young females using characteristic parameters

作　　者：钟泽君 张贝贝 徐凯忆 王若雯 顾冰菲 ZHONG Zejun;ZHANG Beibei;XU Kaiyi;WANG Ruowen;GU Bingfei(School of Fashion Design&Engineering,Zhejiang Sci-Tech University,Hangzhou,Zhejiang 310018,China;Clothing Engineering Research Center of Zhejiang Province,Hangzhou,Zhejiang 310018,China;Key Laboratory of Silk Culture Heritage and Products Design Digital Technology,Ministry of Culture and Tourism,Hangzhou,Zhejiang 310018,China)

机构地区：[1]浙江理工大学服装学院,浙江杭州310018 [2]浙江省服装工程技术研究中心,浙江杭州310018 [3]丝绸文化传承与产品设计数字化技术文化和旅游部重点实验室,浙江杭州310018

出　　处：《纺织学报》2022年第10期148-154,共7页Journal of Textile Research

基　　金：国家自然科学基金项目(61702461,61702460);“纺织之光”中国纺织工业联合会应用基础研究项目(J202007);中国纺织工业联合会科技指导性项目(2018079);浙江理工大学科研业务费专项资金资助项目(2020Q051);国家级大学生创新创业训练计划项目(202110338042)。

摘　　要：为探究青年女性乳房形态区别,提出了乳房边界定义方法以保证乳房形态参数测量的一致性。使用[TC]2三维扫描仪对140名18~25岁在校未婚孕青年女性进行扫描,获取了包括高度、宽度、角度、弧线等28项乳房形态相关参数;通过变异系数和相关性分析筛选出6个影响乳房形态的主要参数作为聚类指标,从乳房立体形态和聚拢程度两方面对乳房形态进行细分;基于乳房形态分类结果,利用Fisher判别函数对样本进行回判验证。结果表明,青年女性乳房形态可分为9类,基于形态判别规则对初始样本数据整体回判的准确率高达97.1%,说明此判别方法具有较高的准确性,为现有的乳房形态研究提供了新思路。In order to study young female′s breast shape discrimination for improving the bra sizing system for the Chinese females,a definition method for defining breast boundary was proposed to ensure the consistency of breast shape measurement indexes.Raw data was collected by scanning 140 female college students using the[TC]2 scanner,and 28 breast measurement values including height,width,angle,and arc were extracted.Analysis of data was conducted by integrating coefficient of variation and correlation analysis methods,and 6 major parameters affecting breast morphology were identified as clustering indexes.K-means cluster was used to categorize the breast shapes into groups from the 3-D shape of the breast,and the breast shape was subdivided by the ratio of gathering degree and the young females′breast shape was divided into 9 categories.Based on the classification results on breast morphology,Fisher criterion function was used to verify the samples.The results show that the accuracy of overall judgment of the initial sample data based on morphological discrimination rules is as high as 97.1%,which shows that this criterion method has high accuracy,providing new ideas for the breast morphology research,and has a positive effect on the progress in the brassiere industry in China.

关 键 词：乳房形态 三维人体测量 聚类分析 聚拢程度 形态判别 

分 类 号：TS941.17[轻工技术与工程—服装设计与工程]