• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Automatic Face and Gesture Recognition >Rapid Synthesis of Massive Face Sets for Improved Face Recognition
【24h】

Rapid Synthesis of Massive Face Sets for Improved Face Recognition

机译：改进面部识别的大规模面套快速合成

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

摘要

Recent work demonstrated that computer graphics techniques can be used to improve face recognition performances by synthesizing multiple new views of faces available in existing face collections. By so doing, more images and more appearance variations are available for training, thereby improving the deep models trained on these images. Similar rendering techniques were also applied at test time to align faces in 3D and reduce appearance variations when comparing faces. These previous results, however, did not consider the computational cost of rendering: At training, rendering millions of face images can be prohibitive; at test time, rendering can quickly become a bottleneck, particularly when multiple images represent a subject. This paper builds on a number of observations which, under certain circumstances, allow rendering new 3D views of faces at a computational cost which is equivalent to simple 2D image warping. We demonstrate this by showing that the run-time of an optimized OpenGL rendering engine is slower than the simple Python implementation we designed for the same purpose. The proposed rendering is used in a face recognition pipeline and tested on the challenging IJB-A and Janus CS2 benchmarks. Our results show that our rendering is not only fast, but improves recognition accuracy.
机译：最近的工作证明，通过合成现有面系列中可用的面孔的多个新视图，可以使用计算机图形技术来改善面部识别性能。通过这样做，更多的图像和更多的外观变化可用于训练，从而改善在这些图像上训练的深层模型。在测试时间上也应用类似的渲染技术以在3D中对准面部并在比较面时降低外观变化。然而，这些以前的结果没有考虑渲染的计算成本：在培训时，渲染数百万的面部图像可能是禁止的;在测试时间时，渲染可以快速成为瓶颈，特别是当多个图像代表主题时。本文在某些情况下构建了许多观察，允许以计算成本呈现面部的新3D视图，这相当于简单的2D图像翘曲。我们通过表明优化的OpenGL渲染引擎的运行时间慢于我们为相同目的设计的简单Python实现慢的运行时间来证明这一点。建议的渲染用于面部识别管道，并在挑战IJB-A和Janus CS2基准测试中进行测试。我们的结果表明，我们的渲染不仅快速，而且提高了识别准确性。

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