文件名称:Robust_Face_Landmark
介绍说明--下载内容均来自于网络,请自行研究使用
在现实世界条件下获取人脸存在较大的变化在形状和遮挡由于不同在姿态、表情、附属品的使用,例如,太阳镜和帽子以及与目标体(e.g. 食物)的交。当前的人脸界标估计方法在这种条件下努力但由于缺乏一种有效的理论方法用于处理局外点。我们提供了一个新奇的方法,称为Robust Cascaded Pose Regression (RCPR),通过检测显式的遮挡且使用鲁棒的形状索引的特征可以减少exposure对于局外点。我们证明RCPR改进先前的界标估计方法在3个通用的人脸数据集上(LFPW, LFW and HELEN)。我们进一步探讨RCPR的性能通过引入一个新奇的人脸数据集集中于遮挡,共由1007幅人脸图像组成,表示了大范围的遮挡模式。RCPR减少失败的案例通过在所有4个数据集上的half,同时,它检测人脸遮挡具有一个80/40 的准确率/召回率。-We propose a novel method, called Robust
Cascaded Pose Regression (RCPR) which reduces exposure
to outliers by detecting occlusions explicitly and using robust shape-indexed features. We show that RCPR improves
on previous landmark estimation methods on three popular face datasets (LFPW, LFW and HELEN). We further
explore RCPR’s performance by introducing a novel face
dataset focused on occlusion, composed of 1,007 faces presenting a wide range of occlusion patterns. RCPR reduces
failure cases by half on all four datasets, at the same time as
it detects face occlusions with a 80/40 precision/recall.
Cascaded Pose Regression (RCPR) which reduces exposure
to outliers by detecting occlusions explicitly and using robust shape-indexed features. We show that RCPR improves
on previous landmark estimation methods on three popular face datasets (LFPW, LFW and HELEN). We further
explore RCPR’s performance by introducing a novel face
dataset focused on occlusion, composed of 1,007 faces presenting a wide range of occlusion patterns. RCPR reduces
failure cases by half on all four datasets, at the same time as
it detects face occlusions with a 80/40 precision/recall.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
Burgos-Artizzu_Robust_Face_Landmark_2013_ICCV_paper.pdf