首页> 外文期刊>Pattern Analysis and Applications >Unsupervised joint face alignment with gradient correlation coefficient
【24h】

Unsupervised joint face alignment with gradient correlation coefficient

机译:具有梯度相关系数的无监督关节面对齐

获取原文
获取原文并翻译 | 示例
           

摘要

This work proposes an unsupervised joint alignment framework, referred to as "Gradient Correlation Congealing," which aligns an image ensemble by maximizing a sum of gradient correlation coefficient function defined over all images. We, respectively, develop two different formulations to optimize the objective function regarding the role of "template." While most existing face alignment methods suffer from outliers, e.g., occlusions, the proposed algorithms are able to align faces undergoing partial occlusions. Moreover, our algorithms can cope with nonuniform illumination changes (even extremely difficult ones), and also, they do not require any predefined templates. We test the novel approaches against four typical joint alignment methods including Least-Squares Congealing, Learned-Miller Congealing, Lucas-Kanade entropy Congealing, and RASL using three challenging face databases: AR, Yale B, and LFW. Experimental results prove the efficiency of our approaches under different conditions, especially when faces are partially occluded, and the proposed algorithms perform much better than all considered methods.
机译:这项工作提出了一种无监督的联合对齐框架,称为“梯度关联凝结”,该框架通过最大化在所有图像上定义的梯度相关系数函数的总和来对齐图像集合。我们分别开发了两种不同的公式来优化关于“模板”作用的目标函数。尽管大多数现有的面部对准方法都具有离群值(例如遮挡),但是所提出的算法能够对准经历部分遮挡的面部。此外,我们的算法可以应对不均匀的照明变化(甚至是非常困难的变化),而且它们不需要任何预定义的模板。我们使用三个具有挑战性的人脸数据库:AR,Yale B和LFW,针对四种典型的联合对准方法(包括最小二乘法,学习米勒凝结,Lucas-Kanade熵凝结和RASL)对新方法进行了测试。实验结果证明了我们的方法在不同条件下的有效性,尤其是在面部被部分遮挡的情况下,所提出的算法比所有考虑的方法都具有更好的性能。

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