{"title":"Intelligent electronic lock with user-defined graphical key","authors":"Yunjiang Hou, Jun Cheng, Wei Feng, X. Zou","doi":"10.1109/ICINFA.2016.7832091","DOIUrl":null,"url":null,"abstract":"In this paper, we present a novel authentication method based on image feature matching to make intelligent lock key can be defined by user which will improve the security and ease-use of intelligent electronic lock. It is a new unlock scheme for intelligent lock that may replaces the text passwords and biological features which are typically used in intelligent lock system. In this method, an object or a digital picture displayed on a physical user-owned device such as a mobile phone can be defined as the intelligent electronic lock key. Firstly, obtain the image of object or digital picture that user defines as the key and the image of the user used for unlocking respectively. Secondly, highly distinctive optical features are extracted from two images and then matching with the features, afterwards the distance between two image's keypoints constitute a discriminant vector. Finally, a LINEAR Support Vector Machine (SVM) is used to classify the discriminant vector. Simulation and experimental results demonstrate the feasibility of proposed approach. The experimental results have obtained satisfactory effect.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE International Conference on Information and Automation (ICIA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICINFA.2016.7832091","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we present a novel authentication method based on image feature matching to make intelligent lock key can be defined by user which will improve the security and ease-use of intelligent electronic lock. It is a new unlock scheme for intelligent lock that may replaces the text passwords and biological features which are typically used in intelligent lock system. In this method, an object or a digital picture displayed on a physical user-owned device such as a mobile phone can be defined as the intelligent electronic lock key. Firstly, obtain the image of object or digital picture that user defines as the key and the image of the user used for unlocking respectively. Secondly, highly distinctive optical features are extracted from two images and then matching with the features, afterwards the distance between two image's keypoints constitute a discriminant vector. Finally, a LINEAR Support Vector Machine (SVM) is used to classify the discriminant vector. Simulation and experimental results demonstrate the feasibility of proposed approach. The experimental results have obtained satisfactory effect.
本文提出了一种新的基于图像特征匹配的认证方法,使用户可以自定义智能电子锁的密钥,从而提高了智能电子锁的安全性和易用性。它是一种新的智能锁解锁方案,可以取代智能锁系统中常用的文本密码和生物特征。在该方法中,在用户拥有的物理设备(如移动电话)上显示的对象或数字图像可以定义为智能电子锁钥匙。首先,分别获取用户定义为密钥的物体图像或数字图像和用于解锁的用户图像。其次,从两幅图像中提取高度显著的光学特征,然后与特征进行匹配,然后将两幅图像关键点之间的距离构成判别向量;最后,利用线性支持向量机(LINEAR Support Vector Machine, SVM)对判别向量进行分类。仿真和实验结果验证了该方法的可行性。实验结果取得了满意的效果。