...
首页> 外文期刊>Sensing and imaging >Local-Friis-Radiation-Pattern (LFRP) for Face Recognition
【24h】

Local-Friis-Radiation-Pattern (LFRP) for Face Recognition

机译:面部识别的本地 - 辐射辐射模式(LFRP)

获取原文
获取原文并翻译 | 示例
           

摘要

In forensic science, various circumstances and requirements give rise to the needfor the development of the inter-modality face recognition system to reinforce lawand order. In this paper, a novel methodology called Local-Friis-Radiation-Pattern(LFRP) for both homogeneous (visible face images with variations like illumination,pose, and makeup) and heterogeneous (near-infrared (NIR)–visible (VIS) andsketch-photo images) face recognition is proposed. LFRP incorporates the renownedFriis equation of antenna radiation and extends it to image pixels to establish a relationamong the pixels residing in a local neighbourhood. Here, we present a robustlocal image descriptor called the LFPR to effectively capture the illumination-invariant,and modality-invariant facial features. Recognition results on CASIA NIR–VIS2.0, CUFSF, LFW, CMU-PIE, Extended Yale B, TUFTS VMU, YMU, and MIWdatabases indicate the superiority and efficiency of the proposed scheme in termsof common feature representation under varying illumination, pose and modality.Moreover, experimental findings reveal that the proposed LFRP is robust againstface recognition under non-permanent facial cosmetics (makeup). On the more,a predefined convolutional neural network architecture has been incorporated toimprove and compare the proposed LFRP feature map with other state-of-the-artdeep learning based methods.
机译:在法医学中,各种情况和需求引起了需求为了强化法律的模态面部识别系统的发展和订单。本文,一种名为局部 - 辐射辐射模式的新型方法(LFRP)对于均匀(可见面部图像,具有含有的变化,姿势和化妆)和异质(近红外(近红外) - 可见(VI)和提出了素描照片图像)面部识别。 LFRP包含着名的天线辐射的Friis方程并将其延伸到图像像素以建立关系在驻留在本地邻居中的像素中。在这里,我们呈现强大的本地图像描述符称为LFPR以有效地捕获照明不变,和模态不变的面部特征。 Casia Nir-Vis的识别结果2.0,CUFSF,LFW,CMU-PIE,延长Yale B,Tufts VMU,YMU和MIW数据库表明所提出的方案的优势和效率不同照明,姿势和模态下的共同特征表示。此外,实验结果表明,所提出的LFRP是强大的非永久性面部化妆品(化妆)下的人脸识别。更频繁,已纳入预定义的卷积神经网络架构改进并比较所提议的LFRP功能图与其他最先进的基于深度学习的方法。

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