纺织学报 ›› 2014, Vol. 35 ›› Issue (5): 113-0.

• 服装工程 • 上一篇    下一篇

基于随机森林的女性体型判别

尹玲1,夏蕾2,许才国1   

    1. 宁波大学艺术学院
    2. 上海工程技术大学服装学院
  • 收稿日期:2013-05-09 修回日期:2014-02-13 出版日期:2014-05-15 发布日期:2014-05-09
  • 通讯作者: 尹玲 E-mail:yinling@nbu.edu.cn
  • 基金资助:

    浙江省教育厅科研项目

Female body shape prediction based on random forest

  • Received:2013-05-09 Revised:2014-02-13 Online:2014-05-15 Published:2014-05-09
  • Contact: Ling Yin E-mail:yinling@nbu.edu.cn

摘要: 针对目前服装行业亟待解决的服装合体性问题,为准确判断用户体型,分析730名年龄在18-50岁之间的女性体型数据,提取表征体型特征的六个重要因子;根据特征因子,从整体、局部和躯干轮廓三个层面对女性体型分类;在此基础上,以随机森林理论算法为基础,以R语言为实现工具,建立女性体型分类判别模型。结果显示,三个随机森林分类器的分类精度都较高,训练样本及测试样本的准确率均在85%以上,表明基于随机森林法建立的女性体型判别模型是可靠的;进一步通过随机森林对变量重要性的评估,筛选出表征女性形体指标的重要特征变量。

关键词: 女性体型, 体型分类, 判别模型, 随机森林, 特征变量

Abstract: Abstract: Clothing fit is a problem of demanding prompt solution in the present apparel industries. In order to determine the true shape of female body accurately, the large number of measurement data of 730 female subjects aging 18-50 was analyzed and six characteristic factors were extracted by factors analysis. Female figure was classified from the three levels, including the whole body type,local morphological characteristics and figure silhouette. According to it, prediction model of female body shape was established by using the algorithm of random forests, and the programmed tool was R language. The results showed that three of the random forest classifiers had high accuracy of prediction, which was up to 85% both for train samples and for test samples. It suggested that the prediction model was reliable for female figure identification. Further, the vital characteristic variables featuring female body shape were filtered by using random forest variable importance measures.

Key words: female body shape, body shape classification, prediction model, random forest, characteristic variables

中图分类号: 

  • TS 941.2
[1] 景晓宁 李晓久. 朴素贝叶斯算法在女童体型判别中的应用[J]. 纺织学报, 2017, 38(12): 124-128.
[2] 姚怡 马静 吴欢 李秦曼 邹奉元. 基于小波系数的青年女性体型分类及原型纸样[J]. 纺织学报, 2017, 38(12): 119-123.
[3] 夏凤勤 毋戈 谢昊洋 钟跃崎. 基于人体纵截面特征曲线的体型分类[J]. 纺织学报, 2017, 38(06): 86-91.
[4] 王祺明. 基于人体三围截面面积的江浙地区女性体型分类[J]. 纺织学报, 2016, 37(05): 131-0.
[5] 尹玲 张文斌 许才国. 基于有序样本最优分割法的女性体型分类[J]. 纺织学报, 2014, 35(9): 114-0.
[6] 吴巧英 冯婉婉. 长江下游地区学龄前女童体型的分类[J]. 纺织学报, 2013, 34(4): 111-116.
[7] 潘力 王军 沙莎 于佐君. 东北地区青年女子体型分类与服装档差研究[J]. 纺织学报, 2013, 34(11): 131-0.
[8] 吴世刚 邹平. 辽宁地区学龄女童体型分类分析[J]. 纺织学报, 2011, 32(9): 104-108.
[9] 齐静;李毅;张欣. 我国西部地区青年男性体型描述与体型分类研究[J]. 纺织学报, 2010, 31(5): 107-111.
[10] 刘咏梅;代虹. 成都地区中老年女性体型研究[J]. 纺织学报, 2010, 31(10): 110-115.
[11] 杨允出;陈敏之;邹奉元. 基于三维扫描数据的女性体型特征参数分析[J]. 纺织学报, 2009, 30(08): 117-122.
[12] 王玉秀;李晓久;刘皓. 二维非接触人体测量中体型的模糊聚类分析[J]. 纺织学报, 2007, 28(2): 100-103.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!