{"title":"An Efficient Cloud-Based Iris Recognition Solution for Mobile Devices","authors":"F. Santos, F. Faria, A. Boukerche, L. Villas","doi":"10.1145/2810362.2810373","DOIUrl":null,"url":null,"abstract":"The use of biological properties for individual identification, called biometric systems, on mobile devices is the easier and safer approach to deal with user personal information. Several works have been sought to develop robust solutions for different biometric modalities, such as, face, fingerprint, palmprint, voice, and iris recognition. In this work, we evaluate three well-know local binary descriptors -- BRIEF, ORB and BRISK -- for iris recognition task. We show that the iris recognition is a computationally heavy task to run locally on mobile devices. Then we propose to perform iris recognition on a cloud infrastructure, which has recently emerged as a new paradigm for hosting and delivering services over the Internet. Moreover, the information processing could be completed much faster. In our experiments, we assessed the effectiveness, time-consuming, and memory usage metrics. Simulation results show that cloud-based iris recognition using WiFi or LTE communication reduces the average time at least 50% in comparison with time obtained to perform the iris recognition locally.","PeriodicalId":332932,"journal":{"name":"Proceedings of the 13th ACM International Symposium on Mobility Management and Wireless Access","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2015-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 13th ACM International Symposium on Mobility Management and Wireless Access","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2810362.2810373","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
The use of biological properties for individual identification, called biometric systems, on mobile devices is the easier and safer approach to deal with user personal information. Several works have been sought to develop robust solutions for different biometric modalities, such as, face, fingerprint, palmprint, voice, and iris recognition. In this work, we evaluate three well-know local binary descriptors -- BRIEF, ORB and BRISK -- for iris recognition task. We show that the iris recognition is a computationally heavy task to run locally on mobile devices. Then we propose to perform iris recognition on a cloud infrastructure, which has recently emerged as a new paradigm for hosting and delivering services over the Internet. Moreover, the information processing could be completed much faster. In our experiments, we assessed the effectiveness, time-consuming, and memory usage metrics. Simulation results show that cloud-based iris recognition using WiFi or LTE communication reduces the average time at least 50% in comparison with time obtained to perform the iris recognition locally.