• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IFIP TC-6 TC-11 International Conference on Communications and Multimedia Security >Multimodal Biometrics for Voice and Handwriting
【24h】

Multimodal Biometrics for Voice and Handwriting

机译：语音和手写的多模式生物识别技术

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper a novel fusion approach for combining voice and online signature verification will be introduced. While the matching algorithm for the speaker identification modality is based on a single Gaussian Mixture Model (GMM) algorithm, the signature verification strategy is based on four different distance measurement functions, combined by multialgorithmic fusion. Together with a feature extraction method presented in our earlier work, the Biometric Hash algorithm, they result in four verification experts for the handwriting subsystem. The fusion results of our new subsystem on the multimodal level are elaborated by enhancements to a system, which was previously introduced by us for biometric authentication in HCI scenarios. Tests have been performed on identical data sets for the original and the enhanced system and the first results presented in this paper show that an increase of recognition accuracy can be achieved by our new multialgorithmic approach for the handwriting modality.
机译：本文将介绍一种用于组合语音和在线签名验证的新型融合方法。虽然扬声器识别模态的匹配算法基于单个高斯混合模型（GMM）算法，但签名验证策略基于四个不同的距离测量功能，通过多颗粒融合组合。与我们之前的工作中提出的特征提取方法一起，生物识别散列算法，它们导致手写子系统的四个验证专家。我们的新子系统对多模级的融合结果是通过对系统的增强来阐述的，以便我们在HCI方案中引入生物识别身份验证。已经对原始数据集进行了测试，并且本文中提出的第一结果表明，通过我们的新多铝仪方法来实现识别准确度的增加，以便我们的手写模态的新多颗粒方法。

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