【24h】

Face Recognition System Using Accurate and Rapid Estimation of Facial Position and Scale

机译:准确快速估计人脸位置和比例的人脸识别系统

获取原文
获取原文并翻译 | 示例

摘要

Face recognition technology needs to be robust for arbitrary facial appearances. In this paper, we propose a face recognition system that is efficient and robust for facial scale variations. In the process of face recognition, facial position detection incurs the highest computational cost. To estimate both facial position and scale, there needs to be a trade-off between accuracy and efficiency. To resolve the trade-off, we propose a method that estimates facial position in parallel with facial scale. We apply the method to our proposed system and demonstrate the advantages of the proposed system through face recognition experiments. The proposed system is more efficient than any other system and can maintain high face recognition accuracy for facial scale variations.
机译:面部识别技术必须具有鲁棒性,以适应任意面部外观。在本文中,我们提出了一种有效且鲁棒的面部比例变化的面部识别系统。在面部识别过程中,面部位置检测会产生最高的计算成本。为了估计面部位置和比例,需要在准确性和效率之间进行权衡。为了解决这个问题,我们提出了一种与面部比例尺平行估计面部位置的方法。我们将该方法应用于我们提出的系统,并通过面部识别实验证明了提出系统的优势。所提出的系统比任何其他系统更有效,并且可以针对面部比例变化保持较高的面部识别精度。

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