Stability Study Of Plantar Pressure In Natural Walking State

The study of plantar pressure is becoming more and more popular in the field of human-computer interaction,clinical medicine and other fields.Only each of the plantar pressure is stable,personalized,plantar pressure identification is scientific,but the stability problem of the plantar pressure has not been verified.In the public security practice footprints can be were personal identification,but there is no underlying scientific principles as the theoretical support.To process the collected data by computer programming,so as to prove the data of plantar pressure of normal person is basically stable.Use MATLAB software to conduct the dynamic plantar pressure's peak data table that acquired by FOOTSCAN plantar pressure measurement and analysis system,and use statistical correlation algorithm and to deal with,so as to analysis the stability of plantar pressure quantitatively,it can be used to study and apply by the plantar pressure data.Three methods were used to investigate the stability of the plantar pressure under the condition of natural walking.First,the variance analysis of plantar pressure characteristics.Firstly,established the plantar pressure database and pretreatment of the foot pressure peak data table,obtained the minimum plantar pressure matrix,then the plantar part is divided into three regions,as the toe area,forefoot area and heel area,the pressure center point of each region is calculated by using the pressure formula,and then the minimum plantar pressure matrix is normalized by the image rotation algorithm so as to rotate the plantar pressure image to the same latitude.At last,the algorithm of variance analysis of the plantar pressure characteristics is used to analyze the variance of the plantar pressure,so as to research the stability of the plantar pressure.Second,the variance analysis of the Euclidean distance of plantar pressure.With the same method to pretreat the plantar pressure's peak data,get the minimum plantar pressure matrix,and divided the plantar part into three regions,named the toe area,forefoot area and heel area.And then use the pressure formula to calculate the center point of pressure of the foot pressure,and calculate the pressure center point of each region.Finally,using the Euclidean distance formula to calculate the feature vector of the center point of plantar pressure to the overall regional center point of plantar pressure.The variance of the Euclidean distance vector of the same plantar pressure of each person is calculated,and then the stability of the plantar pressure is analyzed,so as to analyze the stability of the plantar pressure.Third,the method of color histogram.he main function of color histogram is to describe the color feature of the image,and get the proportion of different colors in the image.Using the FOOTSCAN plantar pressure measurement and analysis system to get the image of plantar pressure regional distribution,calculate the color histogram of regional distribution of plantar pressure of each individual,and compare the similarity with different plantar color histogram of the same foot but from different tester.Through the analysis of the area of plantar pressure,so as to analyze the stability of the plantar pressure.Finally,using the SVM classifier,based on the stability of the foot pressure,the pressure data samples of 100 testers were trained and identified to achieve the purpose of identification using the plantar pressure.After analyzing we conclude that the stability of plantar pressure under the condition of natural walking is good,and it can be used for automatic identification.In this experiment,the accuracy of the automatic identification of plantar pressure was 88.67%.