Discriminative Face Alignment
Discriminative Face Alignment
复制标题
DOI：
10.1109/tpami.2008.238
复制
发表时间：
2009-11-01
影响因子：
23.6
通讯作者：
Liu, Xiaoming
中科院分区：
文献类型：
--
作者：
Liu, Xiaoming
本文提出了一种判别式的框架，有效地对齐图像。尽管传统的基于主动外观模型（AAM）的方法已经取得了一些成功，但是它们遭受泛化问题，即，如何将任何图像与通用模型对齐。我们把迭代图像对齐问题看作是一个训练好的两类分类器的得分最大化的过程，该两类分类器能够区分正确的对齐（阳性类）和不正确的对齐（阴性类）。在建模阶段，给定一组具有地面真实地标的图像，我们训练传统的点分布模型（PDM）和基于增强的分类器，该分类器用作外观模型。当在具有初始标志位置的图像上进行测试时，所提出的算法通过梯度上升方法迭代地更新PDM的形状参数，使得翘曲图像的分类得分最大化。我们使用术语Boosted Appearance Models（BAM）来指代学习的形状和外观模型，以及我们特定的对齐方法。该框架被应用到人脸对齐问题。通过大量的实验，我们表明，相比基于AAM的方法，该框架大大提高了人脸对齐的鲁棒性，准确性和效率，特别是对于看不见的数据。
This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAMs)-based approaches have achieved some success, they suffer from the generalization problem, i.e., how to align any image with a generic model. We treat the iterative image alignment problem as a process of maximizing the score of a trained two-class classifier that is able to distinguish correct alignment (positive class) from incorrect alignment (negative class). During the modeling stage, given a set of images with ground truth landmarks, we train a conventional Point Distribution Model (PDM) and a boosting-based classifier, which acts as an appearance model. When tested on an image with the initial landmark locations, the proposed algorithm iteratively updates the shape parameters of the PDM via the gradient ascent method such that the classification score of the warped image is maximized. We use the term Boosted Appearance Models (BAMs) to refer to the learned shape and appearance models, as well as our specific alignment method. The proposed framework is applied to the face alignment problem. Using extensive experimentation, we show that, compared to the AAM-based approach, this framework greatly improves the robustness, accuracy, and efficiency of face alignment by a large margin, especially for unseen data.