Abstract
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.
Original language | English |
---|---|
Title of host publication | 2015 IEEE International Conference on Digital Signal Processing (DSP) |
Publisher | IEEE |
Pages | 1237-1241 |
Number of pages | 5 |
ISBN (Electronic) | 9781479980581 |
DOIs | |
Publication status | Published - 10 Sept 2015 |
Event | 2015 IEEE International Conference on Digital Signal Processing - Singapore, Singapore Duration: 21 Jul 2015 → 24 Jul 2015 |
Conference
Conference | 2015 IEEE International Conference on Digital Signal Processing |
---|---|
Abbreviated title | DSP 2015 |
Country/Territory | Singapore |
City | Singapore |
Period | 21/07/15 → 24/07/15 |
Keywords
- facial micro-expressions
- Monogenic signal
- quaternion representation
- Riesz wavelet transform
- UFO-MKL
ASJC Scopus subject areas
- Signal Processing