Deformable Templates for Face Description, Recognition, Interpretation, and Learning

这是一项为期三年的持续拨款的第一年，通过制定新的建模和匹配算法，研究光照、反照率、几何形状和视点变化下的鲁棒人脸识别问题。该方法包括推导模型集，当插值时，用于处理视点的广泛变化。所使用的模型由两部分组成：一是与空间变化、个体和表情变化相关的几何模型，二是处理光照和反照率变化的成像模型。研究包括以下四个目标：1)设计、测试和实现将模型与正面视图匹配的算法，2)扩展可变形模板技术，用于跟踪人脸及其特征，并根据表达式确定解释性映射，3)开发概率方法，首先从数据库中学习可变形模板使用的先验分布，然后，开发一种学习方法来确定模型的最大后验估计；4)将模型推广到复杂视觉场景中的多个人脸检测，并且即使在存在异常值和遮挡物的情况下也能表现出鲁棒性。

9317670 Yuille This is the first year funding of a three-year continuing award to investigate the problems of robust face recognition under lighting, albedo, geometry and viewpoint variations by formulating new modeling and matching alogrithms. The approach consists of deriving sets of models which, when interpolated, serve to handle wide variations in viewpoint. The model used consists of two parts: first, a geometric model related to spatial variations and individual and expression changes, and second, an imaging model, which handles variations in lighting and albedo. The research involves the following four goals: 1) the design, test, and implementation of algorithms to match the model described against frontally-viewed faces, 2) the extension of deformable template techniques for tracking faces and their features and determine an interpretative mapping in terms of expressions, 3) the development of probabilistic methodologies for first learning from a database the prior distributions used by deformable templates, and later, to develop a learning method to determine the maximum a posteriori estimate of the model, and 4) to generalize the model to detect multiple faces in complex visual scenes, and perform robustly even in the presence of outliers and occluders.