Robust Face Alignment Using a Mixture of Invariant Experts
Robust Face Alignment Using a Mixture of Invariant Experts
复制标题
DOI：
10.1007/978-3-319-46454-1_50
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Oncel Tuzel;Tim K. Marks;S. Tambe
中科院分区：
文献类型：
--
作者：
Oncel Tuzel;Tim K. Marks;S. Tambe
人脸对齐是在人脸图像中找到一组人脸标志点的位置的任务，在广泛的应用领域中是有用的。当姿态（平面内和平面外旋转）和面部表情存在较大变化时，面部对齐尤其具有挑战性。为了解决这个问题，我们提出了一个级联，其中每个阶段由回归专家的混合物。每个专家学习一个定制的回归模型，该模型专用于姿势和表情的联合空间的不同子集。该系统对于预定义的变换类是不变的（例如，仿射），因为在应用回归之前，输入会被转换以匹配每个专家的原型形状。我们还提出了一种方法，包括变形的歧视性对齐框架内的约束，这使得我们的算法更强大。我们的算法显着优于以前的方法公开可用的人脸对齐数据集。
Face alignment, which is the task of finding the locations of a set of facial landmark points in an image of a face, is useful in widespread application areas. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a mixture of regression experts. Each expert learns a customized regression model that is specialized to a different subset of the joint space of pose and expressions. The system is invariant to a predefined class of transformations (e.g., affine), because the input is transformed to match each expert’s prototype shape before the regression is applied. We also present a method to include deformation constraints within the discriminative alignment framework, which makes our algorithm more robust. Our algorithm significantly outperforms previous methods on publicly available face alignment datasets.