基于热释电红外信息的人体身份识别研究(英文)  

Research on human identity recognition based on pyroelectric infrared information

作　　者：张力新[1] 李佳佳[1] 杨轶星[1] 何峰[1] 王威杰[2] 明东[1] 

机构地区：[1]天津大学生物医学工程与科学仪器系,天津300072 [2]邓迪大学矫形及创伤外科学系,英国300000

出　　处：《仪器仪表学报》2014年第7期1571-1577,共7页Chinese Journal of Scientific Instrument

基　　金：Supported by National Natural Science Foundation of China(81222021,31271062,61172008,81171423,51007063);National Key Technology R&D Program of the Ministry of Science and Technology of China(2012BAI34B02);Program for New Century Excellent Talentsin University of the Ministry of Education of China(NCET-10-0618)

摘　　要：设计并实现了一套由热释电传感器和编码的菲涅尔透镜组成的生物特征跟踪识别系统。对传感器得到的生物信号采用了2种方法提取特征:一种是时域方法,即通过AR模型提取自回归系数;另一种是频域方法,即通过主成分分析后的傅里叶变换提取频谱信息。最后采用支持向量机的方法分别验证了2种特征的识别性能。16名受试者在3种行走速度实验环境下的初步结果显示,时域特征的正确识别率为66.48%,而频域特征的识别率则达到了86.5%。上述结果表明了热释电信息用于人体身份识别的潜能,并证明了个体差异与步态频率信息的强相关性。A biometric tracking and recognition system was designed and implemented, which consists of a pyroelectric infrared （PIR） detector and a coded Fresnel lens array. Two feature extraction methods were developed to extract the features of the biometric data gathered from the sensor for recognition. One is the time-domain feature extraction method, which uses AR model to extract the auto-regressive （AR） coefficients. Another is the frequency-domain feature extraction method, which uses the Fourier Transform with dimensionality reduction by principal component analysis （PCA） to obtain the spectrum matrix information. A support vector machine （SVM） was used to verify the recognition performances of these two feature extraction methods. Preliminary recognition results for 16 subjects with three different walking speeds show that the probability of correct recognition reaches 66.48% for time-domain feature method and 86.5% for frequency-domain feature method. The above results indicate the potential of pyroelectric infrared signals for human identity recognition, and prove the correlation between individual difference factors and gait frequency information.

关 键 词：热释电红外探测器 AR模型 傅里叶变换 主成分分析 支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]