...
首页> 外文期刊>International journal of software science and computational intelligence >Feature and Rank Level Fusion for Privacy Preserved Multi-Biometric System
【24h】

Feature and Rank Level Fusion for Privacy Preserved Multi-Biometric System

机译:隐私保护的多生物特征系统的特征和等级级别融合

获取原文
获取原文并翻译 | 示例
           

摘要

Privacy protection in biometric system is a newly emerging biometric technology that can provide the protection against various attacks by intruders. In this paper, the authors have presented a multi-level of random projection method based on face and ear biometric traits. Privacy preserved templates are used in the proposed system. The main idea behind the privacy preserve computation is the random projection algorithm. Multiple random projection matrixes are used to generate multiple templates for biometric authentication. Newly introduced random fusion method is used in the proposed system: therefore, proposed method can provide better template security, privacy and feature quality. Multiple randomly fused templates are used for recognition purpose and finally decision fusion is applied to generate the final classification result. The proposed method works in a similar way human cognition for face recognition works, furthermore it preserve privacy and multimodality of the system.
机译:生物识别系统中的隐私保护是一种新兴的生物识别技术,可以提供针对入侵者的各种攻击的保护。在本文中,作者提出了一种基于面部和耳朵生物特征的多层次随机投影方法。在建议的系统中使用了保留隐私的模板。隐私保护计算背后的主要思想是随机投影算法。多个随机投影矩阵用于生成用于生物认证的多个模板。提出的系统中使用了新引入的随机融合方法:因此,提出的方法可以提供更好的模板安全性,隐私性和特征质量。将多个随机融合的模板用于识别目的,最后应用决策融合生成最终的分类结果。所提出的方法以类似于人脸识别的人类认知方式工作,此外,它还保留了系统的隐私性和多模式性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号