Facial Expression Recognition Method Based on Difference Center-Symmetric Local Directional Pattern
- 10.2991/cnci-19.2019.27How to use a DOI?
- Local directional pattern, feature extraction, difference center-symmetric local directional pattern, Kirsch operator.
To solve the problem of insufficient feature extraction and low feature extraction efficiency of local directional pattern, this paper proposes a new facial expression extraction method based on difference center-symmetric local directional pattern (DCS-LDP). The grey values in the fields of neighborhood convolved with eight Kirsch operators to obtain eight edge response values. Combining the mean grey values of neighborhood, the response values are compared in three gradient directions of horizontal, vertical and diagonal. The proposed algorithm makes full use of the edge gradient information and extracts multi-level information of facial features on the gradient space. In the recognition step, SVM (support vector machine) is employed to classify facial expressions. The method is tested on CK+ facial expression database and the simulation results show that the method is effective, feasible and robust.
- © 2019, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Yang Jiao AU - Xuefei Jia AU - Junxi Zhao PY - 2019/05 DA - 2019/05 TI - Facial Expression Recognition Method Based on Difference Center-Symmetric Local Directional Pattern BT - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019) PB - Atlantis Press SP - 199 EP - 202 SN - 2352-538X UR - https://doi.org/10.2991/cnci-19.2019.27 DO - 10.2991/cnci-19.2019.27 ID - Jiao2019/05 ER -