中国组织工程研究 ›› 2023, Vol. 27 ›› Issue (4): 527-533.doi: 10.12307/2022.801

• 骨与关节生物力学 bone and joint biomechanics • 上一篇    下一篇

基于足底压力图像的足型识别算法

鲍文霞1,詹东歌1,王  年1,杨先军2,丁呈彪3   

  1. 1安徽大学电子信息工程学院,安徽省合肥市   230601;2中国科学院合肥物质科学研究院,安徽省合肥市   230031;3安徽医科大学第二附属医院康复医学科,安徽省合肥市   230601
  • 收稿日期:2021-09-24 接受日期:2021-11-11 出版日期:2023-02-08 发布日期:2022-06-22
  • 通讯作者: 王年,博士,教授,博士生导师,安徽大学电子信息工程学院,安徽省合肥市 230601
  • 作者简介:鲍文霞,女,1980年生,安徽省铜陵市人,2010年安徽大学毕业,博士,副教授,硕士生导师,主要从事模式识别、计算机视觉研究。
  • 基金资助:
    国家重点研发计划资助项目(2020YFF0303803),项目负责人:鲍文霞

Foot-type recognition algorithm based on plantar pressure images

Bao Wenxia1, Zhan Dongge1, Wang Nian1, Yang Xianjun2, Ding Chengbiao3   

  1. 1School of Electronic Information Engineering, Anhui University, Hefei 230601, Anhui Province, China; 2Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, Anhui Province, China; 3Department of Rehabilitation Medicine, The Second Hospital of Anhui Medical University, Hefei 230601, Anhui Province, China
  • Received:2021-09-24 Accepted:2021-11-11 Online:2023-02-08 Published:2022-06-22
  • Contact: Wang Nian, MD, Professor, Doctoral supervisor, School of Electronic Information Engineering, Anhui University, Hefei 230601, Anhui Province, China
  • About author:Bao Wenxia, MD, Associate professor, Master’s supervisor, School of Electronic Information Engineering, Anhui University, Hefei 230601, Anhui Province, China
  • Supported by:
    the State Key Program for Research and Development of China, No. 2020YFF0303803 (to BWX)

摘要:

文题释义:
足弓中断(interrupt the foot,ITF):是此次研究设计的一种判断足弓是否中断的特征,通过对足底压力图像足弓部位的像素点进行扫描,‘是’代表足弓中断,输出特征为‘1’,即判断为高弓足的特征;‘否’代表足弓部连续,输出特征为‘0’,判断为扁平足或正常足的特征之一。
梯度提升决策树(gradient boosted decision tree,GBDT):是一种迭代的决策树算法,该算法由多棵决策树组成,提升方法是从基学习器出发,反复学习,得到一系列基分类器,对这些基分类器进行组合,得到一个强分类器的过程,并对该文的3种足型进行分类识别。

背景:足弓在人体活动中起着支撑和缓冲的作用,足弓异常会引起运动障碍和下肢疼痛。准确识别病态足型是做出相应的预防、护理矫正措施的前提。
目的:提取常用的四大足型特征,并设计足弓中断特征,联合梯度提升决策树分类器,验证足型识别的准确率。
方法:采集了45人的1 710幅足底压力图像,包括高弓足、扁平足和正常足3种足型。分别提取足底压力图像的足弓指数、脚印系数、足弓宽度以及比值系数等不同特征,同时设计了足弓中断特征,并利用梯度提升决策树(GBDT)算法实现对足底压力图像的不同足型进行识别。
结果与结论:在所构建的45人的1 710幅足底压力图像数据集上,该文章算法的足型平均识别准确率达到了96.43%,高于目前基于足弓指数、脚印系数、足弓宽度以及比值系数等常用的足型判断方法。
缩略语:梯度提升决策树:gradient boosted decision tree,GBDT

https://orcid.org/0000-0002-0536-1556 (鲍文霞)

中国组织工程研究杂志出版内容重点:人工关节;骨植入物;脊柱;骨折;内固定;数字化骨科;组织工程

关键词: 足型识别, 足弓, 高弓足, 扁平足, 足型特征, GBDT

Abstract: BACKGROUND: The arch of the foot plays a supporting and cushioning role in people’s daily physical activities. The abnormal arch of the foot can cause movement disorders and lower limb pain. It is the premise of making the corresponding prevention and nursing corrective measures to accurately identify the pathological foot type. 
OBJECTIVE: The accuracy of foot recognition can be improved effectively by extracting common features of quadrupedal foot and designing foot interruption feature combined with gradient boosted decision tree classifier. 
METHODS: Totally 1 710 plantar pressure images of 45 people were collected, including high-arch, flat and normal foot. Arch index, footprint index, arch width, and ratio index of plantar pressure images were extracted respectively. At the same time, the foot interruption feature was designed, and the gradient boosted decision tree algorithm was used to recognize different foot types of plantar pressure images.
RESULTS AND CONCLUSION: On the constructed data set of 1 710 plantar pressure images of 45 people, the average recognition accuracy of the proposed algorithm reached 96.43%, which was higher than the current commonly used methods based on arch index, footprint index, arch width, and ratio index.  

Key words: foot-type recognition, foot-arch, high-arch, flat foot, foot type features, gradient boosted decision tree

中图分类号: