首页> 外文会议>International Conference on Computer and Communication Engineering >Convolutional Neural Network-based Finger Vein Recognition using Near Infrared Images
【24h】

Convolutional Neural Network-based Finger Vein Recognition using Near Infrared Images

机译:基于卷积神经网络的近红外图像手指​​静脉识别

获取原文

摘要

Convolutional Neural Network (CNN) is opening new horizons in biometrics-based authentication field and finger vein recognition is the prominent one which can provide the best possible security system depending on this aforementioned technology. In this paper, we used 5 convolutional layers and 4 fully-connected layers where our developed network has shown the capability to produce the result with almost 100% accuracy rate which became possible due to the fact that deep learning, an end-to-end system is used which performs better in a lot of aspects in comparison to conventional techniques.
机译:卷积神经网络(CNN)在基于生物识别的身份验证领域开辟了新的视野,而手指静脉识别则是最重要的技术,它可以根据上述技术提供最佳的安全系统。在本文中,我们使用了5个卷积层和4个全连接层,其中我们开发的网络显示出能够以几乎100%的准确率产生结果的能力,这是因为深度学习,端到端的事实使用了与传统技术相比在许多方面表现更好的系统。

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