{"title":"基于svm的体内传播信号生物特征认证","authors":"I. Nakanishi, Yuuta Sodani","doi":"10.1109/AVSS.2010.12","DOIUrl":null,"url":null,"abstract":"To use intra-body propagation signals for biometric authenticationhave been proposed. The intra-body propagationsignals are hid in human bodies; therefore, they havetolerability to circumvention using artifacts. Additionally,utilizing the signals in the body enables liveness detectionwith no additional scheme. The problem is, however, verificationperformance using the intra-body propagation signalis not so high. In this paper, in order to improve the performancewe propose to use user-specific frequency bandsfor all users in verification. The verification performance isimproved to 70 %. Furthermore, we introduce the supportvector machine (SVM) into the verification process. It isconfirmed that verification rate of about 86 % is achieved.","PeriodicalId":415758,"journal":{"name":"2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance","volume":"74 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"SVM-Based Biometric Authentication Using Intra-Body Propagation Signals\",\"authors\":\"I. Nakanishi, Yuuta Sodani\",\"doi\":\"10.1109/AVSS.2010.12\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To use intra-body propagation signals for biometric authenticationhave been proposed. The intra-body propagationsignals are hid in human bodies; therefore, they havetolerability to circumvention using artifacts. Additionally,utilizing the signals in the body enables liveness detectionwith no additional scheme. The problem is, however, verificationperformance using the intra-body propagation signalis not so high. In this paper, in order to improve the performancewe propose to use user-specific frequency bandsfor all users in verification. The verification performance isimproved to 70 %. Furthermore, we introduce the supportvector machine (SVM) into the verification process. It isconfirmed that verification rate of about 86 % is achieved.\",\"PeriodicalId\":415758,\"journal\":{\"name\":\"2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance\",\"volume\":\"74 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AVSS.2010.12\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AVSS.2010.12","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
SVM-Based Biometric Authentication Using Intra-Body Propagation Signals
To use intra-body propagation signals for biometric authenticationhave been proposed. The intra-body propagationsignals are hid in human bodies; therefore, they havetolerability to circumvention using artifacts. Additionally,utilizing the signals in the body enables liveness detectionwith no additional scheme. The problem is, however, verificationperformance using the intra-body propagation signalis not so high. In this paper, in order to improve the performancewe propose to use user-specific frequency bandsfor all users in verification. The verification performance isimproved to 70 %. Furthermore, we introduce the supportvector machine (SVM) into the verification process. It isconfirmed that verification rate of about 86 % is achieved.