首页> 外国专利> METHOD AND SYSTEM FOR PREDICTING SHAPE OF HUMAN BODY AFTER TREATMENT

METHOD AND SYSTEM FOR PREDICTING SHAPE OF HUMAN BODY AFTER TREATMENT

机译:处理后人体形状的预测方法和系统

摘要

The objective of the present invention is to use arithmetic processing to predict simply and accurately the shape of a human body after treatment.This method includes: a step of extracting a feature vector Fnew from face data of a patient being evaluated; a step of selecting a plurality of case patients having feature vectors Fpre(i), extracted from the face data of a plurality of previous patients, that are a short distance from the feature vector Fnew, or a step of selecting an approximated case class having a cluster center of gravity Gpre(l) that is a short distance from the feature vector Fnew; a step of obtaining pre-correction face shape models Hpre(i) and post-correction face shape models Hpost(i) in which the faces of the selected previous case patients before and after treatment have been normalized; a step of obtaining a face shape model Hnew in which the face of the patient being evaluated has been normalized; and a step of obtaining a three-dimensional predicted face shape model Hprd as predicted after correction, by modifying the face shape model Hnew of the patient being evaluated, using a vector average difference AVEpost-AVEpre between the pre-treatment and post-treatment face shape models of case patients having a face shape similar to that of the patient being evaluated.
机译:本发明的目的是使用算术处理来简单且准确地预测治疗后的人体形状。该方法包括:从被评估患者的面部数据中提取特征向量Fnew的步骤;从多个先前患者的面部数据中提取特征向量Fpre(i)的多个病例患者的步骤,这些特征患者距离特征向量Fnew短距离,或者选择具有以下特征的近似病例类别的步骤:距特征向量Fnew短距离的簇重心Gpre(l);获得校正前的脸部形状模型Hpre(i)和校正后的脸部形状模型Hpost(i)的步骤,其中所选择的先前病例患者在治疗之前和之后的面部已经被标准化;获得面部形状模型Hnew的步骤,其中,被评估患者的面部已经被标准化;通过修改治疗前和治疗后面部之间的矢量平均差AVEpost-AVEpre,通过修改被评估患者的面部形状模型Hnew,获得校正后预测的三维预测面部形状模型Hprd的步骤病例患者的脸部形状模型与正在评估的患者相似。

著录项

  • 公开/公告号WO2017069231A1

    专利类型

  • 公开/公告日2017-04-27

    原文格式PDF

  • 申请/专利权人 OSAKA UNIVERSITY;

    申请/专利号WO2016JP81236

  • 发明设计人 TANIKAWA CHIHIRO;TAKADA KENJI;

    申请日2016-10-21

  • 分类号A61C7;

  • 国家 WO

  • 入库时间 2022-08-21 13:31:16

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号