Learning From Hierarchical Spatiotemporal Descriptors for Micro-Expression Recognition
Learning From Hierarchical Spatiotemporal Descriptors for Micro-Expression Recognition
复制标题
DOI：
10.1109/tmm.2018.2820321
复制
发表时间：
2018-03
影响因子：
7.3
通讯作者：
Yuan Zong;Xiaohua Huang;Wenming Zheng;Zhen Cui;Guoying Zhao
中科院分区：
文献类型：
--
作者：
Yuan Zong;Xiaohua Huang;Wenming Zheng;Zhen Cui;Guoying Zhao
微表情识别旨在推断人们试图从面部视频片段中隐藏的真实情绪。这是一项非常具有挑战性的任务，因为微表情的强度很低，持续时间很短，这使得微表情很难被观察到。近年来，研究人员设计了各种时空描述符来描述微表情。值得注意的是，为了更好地捕捉低强度的面部肌肉运动，在提取描述符之前，通常使用固定的空间划分网格，例如$8\ × 8$，将面部图像划分为几个面部块。然而，由于划分网格会影响时空描述符对微表情的区分能力，因此很难针对不同的微表情样本选择理想的划分网格。为了解决这一问题，本文设计了一种用于时空描述符提取的分层空间分割方案。采用该方案，对于不同的微表情样本，确定最适合的划分网格不再是问题。此外，我们提出了一个核化组稀疏学习（KGSL）模型来处理基于层次方案的时空描述符，使它们更有效地用于微表情识别任务。为了评估基于时空描述符和KGSL的层次结构微表情识别方法的性能，在CASME II和SMIC两个公共微表情数据库上进行了大量实验。与许多最新的方法相比，我们的方法获得了更有希望的识别结果。
Micro-expression recognition aims to infer genuine emotions that people try to conceal from facial video clips. It is a very challenging task because micro-expressions have a very low intensity and short duration, which makes micro-expressions difficult to observe. Recently, researchers have designed various spatiotemporal descriptors to describe micro-expressions. It is notable that for better capturing the low-intensity facial muscle movement, a fixed spatial division grid, $8\times 8$ for example, is commonly used to partition the facial images into a few facial blocks before extracting descriptors. However, it is hard to choose an ideal division grid for different micro-expression samples because the division grids affect the discriminative ability of spatiotemporal descriptors to distinguish micro-expressions. To address this problem, in this paper, we design a hierarchical spatial division scheme for spatiotemporal descriptor extraction. By using the proposed scheme, it would not be a problem to determine which division grid is most suitable regarding different micro-expression samples. Furthermore, we propose a kernelized group sparse learning (KGSL) model to process hierarchical scheme based spatiotemporal descriptors such that they are more effective for micro-expression recognition tasks. To evaluate the performance of the proposed micro-expression recognition method consisting of the hierarchical scheme based spatiotemporal descriptors and KGSL, extensive experiments are conducted on two public micro-expression databases: CASME II and SMIC. Compared with many recent state-of-the-art approaches, our method achieves more promising recognition results.