Valstar Michel F, Pantic Maja
Department of Computing, Imperial College London, SW7 2AZ London, U.K.
IEEE Trans Syst Man Cybern B Cybern. 2012 Feb;42(1):28-43. doi: 10.1109/TSMCB.2011.2163710. Epub 2011 Sep 15.
Past work on automatic analysis of facial expressions has focused mostly on detecting prototypic expressions of basic emotions like happiness and anger. The method proposed here enables the detection of a much larger range of facial behavior by recognizing facial muscle actions [action units (AUs)] that compound expressions. AUs are agnostic, leaving the inference about conveyed intent to higher order decision making (e.g., emotion recognition). The proposed fully automatic method not only allows the recognition of 22 AUs but also explicitly models their temporal characteristics (i.e., sequences of temporal segments: neutral, onset, apex, and offset). To do so, it uses a facial point detector based on Gabor-feature-based boosted classifiers to automatically localize 20 facial fiducial points. These points are tracked through a sequence of images using a method called particle filtering with factorized likelihoods. To encode AUs and their temporal activation models based on the tracking data, it applies a combination of GentleBoost, support vector machines, and hidden Markov models. We attain an average AU recognition rate of 95.3% when tested on a benchmark set of deliberately displayed facial expressions and 72% when tested on spontaneous expressions.
过去关于面部表情自动分析的研究主要集中在检测诸如快乐和愤怒等基本情绪的典型表情上。本文提出的方法通过识别构成表情的面部肌肉动作（动作单元，简称AUs），能够检测范围更广的面部行为。动作单元是客观的，将对所传达意图的推断留给更高层次的决策（例如，情绪识别）。所提出的全自动方法不仅能够识别22种动作单元，还能明确地对其时间特征（即时间片段序列：中性、起始、顶点和结束）进行建模。为此，它使用基于Gabor特征增强分类器的面部点检测器自动定位20个面部基准点。通过一种称为带分解似然的粒子滤波方法，在一系列图像中跟踪这些点。为了基于跟踪数据对面部动作单元及其时间激活模型进行编码，该方法结合了GentleBoost、支持向量机和隐马尔可夫模型。在一组故意展示的面部表情基准测试集上进行测试时，我们获得的动作单元平均识别率为95.3%，在自发表情测试中为72%。
