Monogenic Riesz wavelet representation for micro-expression recognition
Monogenic Riesz wavelet representation for micro-expression recognition
复制标题
DOI：
10.1109/icdsp.2015.7252078
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Yee-Hui Oh;A. Ngo;John See;Sze‐Teng Liong;R. Phan;H. Ling
中科院分区：
文献类型：
--
作者：
Yee-Hui Oh;A. Ngo;John See;Sze‐Teng Liong;R. Phan;H. Ling
单演信号是一个二维的分析信号，它提供了幅度，相位和方向的局部信息。虽然它已被应用于面部和表情识别领域[1]，[2]，[3]，但对于微妙的面部微表情还没有已知的用途。在本文中，我们提出了一种特征表示方法，简洁地捕捉这三个低层次的组件在多个尺度。利用Riesz小波变换得到多尺度单演小波，并将其表示为四元数。而不是总结多尺度单演表示，我们认为所有的单演表示在多个尺度作为单独的功能。对于分类，应用两种方案来集成这些多个特征表示：基于融合的方法，使用超快速，优化的多核学习（UFO-MKL）算法有效地和有区别地组合特征;和基于级联的方法，其中特征被组合成单个特征向量并通过线性SVM进行分类。最近自发的微表情数据库上进行的实验表明，所提出的方法优于最先进的单基因信号的方法来解决微表情识别问题的能力。
A monogenic signal is a two-dimensional analytical signal that provides the local information of magnitude, phase, and orientation. While it has been applied on the field of face and expression recognition [1], [2], [3], there are no known usages for subtle facial micro-expressions. In this paper, we propose a feature representation method which succinctly captures these three low-level components at multiple scales. Riesz wavelet transform is employed to obtain multi-scale monogenic wavelets, which are formulated by quaternion representation. Instead of summing up the multi-scale monogenic representations, we consider all monogenic representations across multiple scales as individual features. For classification, two schemes were applied to integrate these multiple feature representations: a fusion-based method which combines the features efficiently and discriminately using the ultra-fast, optimized Multiple Kernel Learning (UFO-MKL) algorithm; and concatenation-based method where the features are combined into a single feature vector and classified by a linear SVM. Experiments carried out on a recent spontaneous micro-expression database demonstrated the capability of the proposed method in outperforming the state-of-the-art monogenic signal approach to solving the micro-expression recognition problem.